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

    Neuronpedia

    INDEX
    Explanations

    probability calculation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     jButton
    -0.07
     bölg
    -0.07
    aju
    -0.07
    '></
    -0.07
     layui
    -0.07
     Haj
    -0.06
    _ANGLE
    -0.06
     floors
    -0.06
    ]‏
    -0.06
     Floor
    -0.06
    POSITIVE LOGITS
    construct
    0.06
    auth
    0.06
     constructs
    0.06
     tả
    0.06
    .absolute
    0.06
     satisfaction
    0.06
    .act
    0.06
    .caption
    0.06
     inexp
    0.06
    exp
    0.06
    Act Density 0.001%

    No Known Activations