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

    Neuronpedia

    INDEX
    Explanations

    action

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Certain
    -1.29
    certain
    -1.16
     certain
    -1.16
     Certain
    -1.16
    Action
    -1.05
     Action
    -0.96
     CERTAIN
    -0.96
     ciertas
    -0.93
     ciertos
    -0.92
     certaine
    -0.85
    POSITIVE LOGITS
    :✨
    0.77
     kasarigan
    0.69
     فريبيس
    0.66
    addCriterion
    0.64
     transfieras
    0.63
    LookAnd
    0.63
    RegressionTest
    0.63
     रूप
    0.57
    SharedCtor
    0.57
     '{@
    0.55
    Act Density 0.047%

    No Known Activations