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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     표
    -0.07
    /issues
    -0.07
    accel
    -0.06
    landır
    -0.06
    .getService
    -0.06
    _PP
    -0.06
     MEP
    -0.06
     heav
    -0.06
    )].
    -0.06
     развити
    -0.06
    POSITIVE LOGITS
    .Companion
    0.08
     captain
    0.07
    ,“
    0.07
    aepernick
    0.06
     prescriptions
    0.06
    ﾝ
    0.06
    oldem
    0.06
    отя
    0.06
     милли
    0.06
     Smithsonian
    0.06
    Act Density 0.008%

    No Known Activations