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

    Neuronpedia

    INDEX
    Explanations

    activity or state

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     friendships
    -0.07
    peq
    -0.06
     siz
    -0.06
     най
    -0.06
     Knee
    -0.06
    _today
    -0.06
     toll
    -0.06
    ListOf
    -0.06
    _AURA
    -0.06
    _modes
    -0.06
    POSITIVE LOGITS
     /.
    0.07
    --------------↵
    0.07
    acre
    0.06
    .dark
    0.06
    /her
    0.06
    hist
    0.06
    ,arg
    0.06
    -го
    0.06
     ′
    0.06
     compromises
    0.06
    Act Density 0.171%

    No Known Activations