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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     grat
    -0.07
     cuanto
    -0.07
     hr
    -0.06
     mourning
    -0.06
     selfie
    -0.06
     unanim
    -0.06
    OMBRE
    -0.06
    .ht
    -0.06
     scient
    -0.06
    )↵
    -0.06
    POSITIVE LOGITS
    .Runtime
    0.06
    ウ
    0.06
    mentions
    0.06
    JSON
    0.06
    ols
    0.06
    (ti
    0.06
    IFY
    0.06
     Kremlin
    0.06
    vice
    0.06
    ref
    0.06
    Act Density 0.000%

    No Known Activations