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

    Neuronpedia

    INDEX
    Explanations

    say "="

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sno
    -0.07
     Justice
    -0.06
     cabo
    -0.06
    _GE
    -0.06
    \Json
    -0.06
     {});↵↵
    -0.06
     ניתן
    -0.06
     Offers
    -0.06
     Switch
    -0.06
    罄
    -0.06
    POSITIVE LOGITS
    :y
    0.08
    CHEMY
    0.07
    𬬩
    0.07
    "H
    0.07
    =cv
    0.07
    .."
    0.07
     hull
    0.07
    (Base
    0.07
    KHTML
    0.07
    ته
    0.07
    Act Density 0.343%

    No Known Activations