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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Coral
    -0.08
     another
    -0.07
    ()*
    -0.07
    undo
    -0.06
     Improvement
    -0.06
     格
    -0.06
    Digits
    -0.06
     Version
    -0.06
    ヽ
    -0.06
    308
    -0.06
    POSITIVE LOGITS
     Jakarta
    0.06
     Tibet
    0.06
    outside
    0.06
     productList
    0.06
     فه
    0.06
     Zionist
    0.06
    ्टम
    0.06
     respectable
    0.05
     Celtic
    0.05
     nullable
    0.05
    Act Density 0.020%

    No Known Activations