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

    Neuronpedia

    INDEX
    Explanations

    -Control

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     edit
    -0.07
    鲁能
    -0.07
    띤
    -0.06
    claimer
    -0.06
    辋
    -0.06
    משחק
    -0.06
     flair
    -0.06
     defaultstate
    -0.06
     Wander
    -0.06
    xmin
    -0.06
    POSITIVE LOGITS
     preservation
    0.08
    .geo
    0.07
     Julian
    0.07
    _alpha
    0.07
    .adjust
    0.07
    法治
    0.07
    宗
    0.07
    adow
    0.07
    .static
    0.07
    Ĉ
    0.07
    Act Density 0.007%

    No Known Activations