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

    Neuronpedia

    INDEX
    Explanations

    bibliographic descriptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     epoxy
    -0.07
    _par
    -0.07
     od
    -0.07
    .viewer
    -0.07
    _recovery
    -0.07
    calar
    -0.07
    _dev
    -0.06
    .Var
    -0.06
     escapes
    -0.06
    ff
    -0.06
    POSITIVE LOGITS
    짠
    0.07
    촘
    0.07
    ()(
    0.07
    emie
    0.07
     >(
    0.07
    ℵ
    0.07
    (chalk
    0.07
    (Position
    0.07
    utzt
    0.06
    (layout
    0.06
    Act Density 0.005%

    No Known Activations