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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Cognitive
    -0.06
     Catholics
    -0.06
    .Department
    -0.06
     AppBar
    -0.06
     Ahmet
    -0.06
     frac
    -0.06
     söyley
    -0.06
     dys
    -0.06
     Mount
    -0.06
     изготов
    -0.06
    POSITIVE LOGITS
     VERY
    0.07
    Searching
    0.06
    649
    0.06
    .',
↵
    0.06
    異
    0.06
     expressions
    0.06
    別
    0.06
    837
    0.06
     육
    0.06
    ويت
    0.06
    Act Density 0.035%

    No Known Activations