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
     outgoing
    -0.08
     Bell
    -0.08
    .partner
    -0.07
     läng
    -0.07
     Parliamentary
    -0.07
    ([
    -0.07
     pari
    -0.07
     prolonged
    -0.07
    _inf
    -0.07
    ೌ
    -0.07
    POSITIVE LOGITS
    COPY
    0.10
    Memcpy
    0.10
     memcpy
    0.09
     COPYING
    0.09
    _COPY
    0.09
     ויש
    0.09
     Derek
    0.09
     වී
    0.09
    ENCY
    0.08
    ienes
    0.08
    Act Density 0.000%

    No Known Activations