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

    Neuronpedia

    INDEX
    Explanations

    not

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     effectivement
    -0.08
     действительно
    -0.08
    织
    -0.07
    ுகள்
    -0.07
    宝
    -0.07
    าก
    -0.07
    ებია
    -0.07
     ekspert
    -0.07
    ალიან
    -0.07
    实时
    -0.07
    POSITIVE LOGITS
     Pourquoi
    0.08
    ;.
    0.08
     Nig
    0.08
     Cas
    0.07
    .Destroy
    0.07
    -Euro
    0.07
     Eur
    0.07
     Humboldt
    0.07
    PRESS
    0.07
     بدون
    0.07
    Act Density 0.000%

    No Known Activations