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

    Neuronpedia

    INDEX
    Explanations

    Code/Programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	day
    -0.07
    (Tag
    -0.07
     "~
    -0.07
    _game
    -0.07
     инфек
    -0.07
    ’y
    -0.07
     войны
    -0.06
    _values
    -0.06
    _AGENT
    -0.06
     felon
    -0.06
    POSITIVE LOGITS
    .external
    0.06
    б
    0.06
     있어
    0.06
    チュ
    0.06
    gio
    0.06
     Geld
    0.06
     白
    0.06
    -single
    0.06
    Neutral
    0.06
     UIImageView
    0.06
    Act Density 0.001%

    No Known Activations