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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    andr
    -0.07
     geen
    -0.07
    Joe
    -0.07
     disappointed
    -0.06
     DATA
    -0.06
     fís
    -0.06
     free
    -0.06
    bite
    -0.06
     Scope
    -0.06
    دارة
    -0.06
    POSITIVE LOGITS
    '^$',
    0.08
     увели
    0.07
    etwork
    0.07
     minlength
    0.07
     �
    0.06
    ﾆﾆ
    0.06
    용
    0.06
    .mkdirs
    0.06
    十四
    0.06
     اصفهان
    0.06
    Act Density 0.012%

    No Known Activations