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

    Neuronpedia

    INDEX
    Explanations

    Quotation marks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (my
    -0.07
     rubbing
    -0.06
     craftsmanship
    -0.06
     Mov
    -0.06
    LPARAM
    -0.06
     tvoř
    -0.06
     URLRequest
    -0.06
    mscorlib
    -0.06
     hypoth
    -0.06
     Fir
    -0.06
    POSITIVE LOGITS
     블
    0.07
    eventName
    0.07
    opens
    0.07
                           ↵
    0.07
    ज
    0.07
     boutique
    0.06
    丁
    0.06
    /↵↵↵↵
    0.06
    lessly
    0.06
    »↵↵
    0.06
    Act Density 0.011%

    No Known Activations