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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _Return
    -0.07
    就会
    -0.07
    Proto
    -0.07
    ToolTip
    -0.07
    (scores
    -0.06
    olated
    -0.06
    stial
    -0.06
    [Double
    -0.06
    ETING
    -0.06
    _weights
    -0.06
    POSITIVE LOGITS
    _ray
    0.07
     kdo
    0.06
     +:+
    0.06
     knowing
    0.06
     tenant
    0.06
    expo
    0.06
    >=
    0.06
    .main
    0.06
     شما
    0.06
     بص
    0.06
    Act Density 0.022%

    No Known Activations