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

    Neuronpedia

    INDEX
    Explanations

    logging code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     �
    -0.08
    ’ta
    -0.06
    .scrollView
    -0.06
     Terminator
    -0.06
     Guerr
    -0.06
     �
    -0.06
    :'
    -0.06
    .Contracts
    -0.06
    头
    -0.06
    社會
    -0.06
    POSITIVE LOGITS
     xPos
    0.07
     uvol
    0.06
     ヾ
    0.06
    وك
    0.06
     Ty
    0.06
    /channel
    0.06
     succes
    0.06
    .socket
    0.06
     effected
    0.06
     derivation
    0.06
    Act Density 0.004%

    No Known Activations