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

    Neuronpedia

    INDEX
    Explanations

    when

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    hire
    -0.08
     pet
    -0.07
    clare
    -0.07
    ент
    -0.07
    _CHARS
    -0.07
    adj
    -0.06
    _SN
    -0.06
     subscriptions
    -0.06
     congratulations
    -0.06
    ipp
    -0.06
    POSITIVE LOGITS
    ^\
    0.07
    .tmp
    0.07
    $n
    0.07
    ../
    0.07
     arreglo
    0.07
    infinity
    0.07
     tabla
    0.07
    带着
    0.07
    _objects
    0.06
     jamais
    0.06
    Act Density 0.000%

    No Known Activations