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

    Neuronpedia

    INDEX
    Explanations

    emphasis

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Inn
    -0.08
    柬埔
    -0.07
     Encounter
    -0.07
    �
    -0.07
    储
    -0.07
     authToken
    -0.07
    Sn
    -0.07
    候选
    -0.07
    Loc
    -0.06
    te
    -0.06
    POSITIVE LOGITS
     emphasis
    0.10
     Julio
    0.08
     emphasize
    0.07
     đa
    0.07
     Newtonsoft
    0.07
    形
    0.07
    مباد
    0.07
    WARNING
    0.07
     Abyss
    0.07
    zial
    0.07
    Act Density 0.010%

    No Known Activations