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

    Neuronpedia

    INDEX
    Explanations

    Newlines

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    key
    -0.07
    Pixel
    -0.07
    χα
    -0.07
    ４
    -0.06
    �
    -0.06
    iliz
    -0.06
    ूद
    -0.06
     Ukrain
    -0.06
    _Data
    -0.06
    _rb
    -0.06
    POSITIVE LOGITS
     Derby
    0.08
     Gilbert
    0.07
     повер
    0.07
     histor
    0.06
     primal
    0.06
     tableau
    0.06
    bert
    0.06
    -----------↵
    0.06
     Radical
    0.06
     Alabama
    0.06
    Act Density 0.007%

    No Known Activations