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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash

    the neuron responds to concrete everyday nouns — common items and things (food, clothing/prints, teams, social-media terms).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Negative Logits
    ули
    -0.07
     expulsion
    -0.06
     Алекс
    -0.06
    enses
    -0.06
     Sparse
    -0.06
    orrar
    -0.06
    xB
    -0.06
     endPoint
    -0.06
    rypt
    -0.06
     ethernet
    -0.06
    POSITIVE LOGITS
    Da
    0.07
     xác
    0.07
     knowingly
    0.07
    .matrix
    0.06
     goggles
    0.06
    yscale
    0.06
    NECT
    0.06
    _trial
    0.06
    ὸ
    0.06
     las
    0.06
    Act Density 0.327%

    No Known Activations