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

    Neuronpedia

    INDEX
    Explanations

    significant amounts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    anon
    -0.11
    ulence
    -0.09
    krv
    -0.09
     conditions
    -0.09
    arker
    -0.09
    Isl
    -0.09
    peq
    -0.09
    ķĮ
    -0.08
    ottom
    -0.08
    NullOr
    -0.08
    POSITIVE LOGITS
     amount
    0.28
     amounts
    0.23
    amount
    0.22
     Amount
    0.18
    -sized
    0.17
     number
    0.16
     enough
    0.16
    Amount
    0.15
     sized
    0.15
    -scale
    0.14
    Act Density 0.048%

    No Known Activations