Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    academic/scientific texts

    np_max-act · gemini-2.0-flash

    words containing the letter 'f' or double consonants.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jdhshshs138

    terms that denote relative order, position, or direction in time or space (e.g., comparative/positional adverbs and descriptors).

    oai_token-act-pair · gpt-5Triggered by @jdhshshs138
    New Auto-Interp
    Negative Logits
    findBy
    -0.07
     ремон
    -0.07
     Stra
    -0.07
    -enable
    -0.06
     свое
    -0.06
     into
    -0.06
     tween
    -0.06
    .setCurrent
    -0.06
     místní
    -0.06
    /*@
    -0.06
    POSITIVE LOGITS
     strained
    0.07
    [K
    0.06
     diced
    0.06
     مخ
    0.06
    (Long
    0.06
     Shot
    0.06
     вой
    0.06
    ấn
    0.06
    (enemy
    0.06
    elay
    0.06
    Act Density 0.000%

    No Known Activations