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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ward
    -0.07
     assort
    -0.06
    ancing
    -0.06
    ile
    -0.06
     lust
    -0.06
     sparing
    -0.06
    ETCH
    -0.06
    _additional
    -0.06
    OPY
    -0.06
     स
    -0.06
    POSITIVE LOGITS
     prostředí
    0.07
     elektrik
    0.07
     трансп
    0.06
    odí
    0.06
    _nonce
    0.06
     Francie
    0.06
    .jquery
    0.06
    Accordion
    0.06
    pf
    0.06
     действия
    0.06
    Act Density 0.020%

    No Known Activations