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

    Neuronpedia

    INDEX
    Explanations

    decision-making

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _square
    -0.06
     itemprop
    -0.06
    yet
    -0.06
    [Y
    -0.06
     Far
    -0.06
    ｊ
    -0.06
    Sym
    -0.06
    xeb
    -0.06
     constr
    -0.06
    ilton
    -0.06
    POSITIVE LOGITS
    ~~
    0.07
    ABL
    0.07
    ).^
    0.07
    charging
    0.06
     roku
    0.06
    .views
    0.06
    _usec
    0.06
    ==(
    0.06
    .gradle
    0.06
     spends
    0.06
    Act Density 0.108%

    No Known Activations