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

    Neuronpedia

    INDEX
    Explanations

    form

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _DIV
    -0.07
    .player
    -0.06
     ترین
    -0.06
    Pr
    -0.06
    adies
    -0.06
     sparkling
    -0.06
     caliente
    -0.06
    绿
    -0.06
     loving
    -0.06
    مند
    -0.06
    POSITIVE LOGITS
     Humans
    0.07
    -Life
    0.07
    Esta
    0.06
    .family
    0.06
    Customer
    0.06
     instinct
    0.06
     Sequence
    0.06
    ographical
    0.06
    ioc
    0.06
    OSH
    0.06
    Act Density 0.010%

    No Known Activations