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

    Neuronpedia

    INDEX
    Explanations

    light

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .StretchImage
    -0.07
     ro
    -0.07
     echang
    -0.06
    _Pos
    -0.06
    _apps
    -0.06
    (HWND
    -0.06
     thép
    -0.06
     Amerik
    -0.06
    _models
    -0.06
    _YES
    -0.06
    POSITIVE LOGITS
    guards
    0.07
     Cody
    0.07
    dit
    0.06
     viewpoints
    0.06
     dictate
    0.06
    .u
    0.06
    ẹn
    0.06
    Sky
    0.06
     justified
    0.06
    StateToProps
    0.06
    Act Density 0.009%

    No Known Activations