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

    Neuronpedia

    INDEX
    Explanations

    control

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     gbc
    -0.07
    _colors
    -0.07
    Built
    -0.07
    (rgb
    -0.07
     fort
    -0.07
     Lip
    -0.06
    скоп
    -0.06
    Founded
    -0.06
     développ
    -0.06
     деп
    -0.06
    POSITIVE LOGITS
     continuation
    0.07
    ()(
    0.07
    Other
    0.07
    _case
    0.07
    �
    0.07
    (',
    0.07
    =.
    0.07
     있다
    0.06
    院子
    0.06
    ++){↵↵
    0.06
    Act Density 0.018%

    No Known Activations