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

    Neuronpedia

    INDEX
    Explanations

    say "direction"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    FREE
    -0.07
     psychologists
    -0.06
    ALES
    -0.06
    ley
    -0.06
    _METHOD
    -0.06
    Data
    -0.06
    ्बन
    -0.06
    _var
    -0.06
    November
    -0.06
    thumb
    -0.06
    POSITIVE LOGITS
     emanc
    0.08
     Гер
    0.07
     Presidential
    0.07
     sharedInstance
    0.07
     Затем
    0.06
    ekkür
    0.06
    .entry
    0.06
    (es
    0.06
    EditingStyle
    0.06
    .party
    0.06
    Act Density 0.011%

    No Known Activations