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

    Neuronpedia

    INDEX
    Explanations

    Avoiding fines/problems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Cameroon
    -0.07
    _conv
    -0.07
     pushed
    -0.07
    attering
    -0.07
    ource
    -0.06
     ног
    -0.06
    sig
    -0.06
    _n
    -0.06
    ."↵↵
    -0.06
    )?↵↵
    -0.06
    POSITIVE LOGITS
     JavaScript
    0.08
     Sessions
    0.06
     liking
    0.06
    pellier
    0.06
    济
    0.06
     maze
    0.06
     Orwell
    0.06
     SHOP
    0.06
    เฮ
    0.06
     همچنین
    0.06
    Act Density 0.005%

    No Known Activations