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

    Neuronpedia

    INDEX
    Explanations

    Physics papers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    :'/
    -0.08
    bidden
    -0.07
    דמה
    -0.07
    =\"%
    -0.07
    /'.
    -0.07
    棕
    -0.07
    ()",
    -0.07
    ('('
    -0.07
    搓
    -0.07
    𬣞
    -0.07
    POSITIVE LOGITS
    ˸
    0.07
    妙
    0.07
     Conduct
    0.07
    八
    0.07
     Alfred
    0.07
     �
    0.07
    קוב
    0.07
     Easily
    0.06
     bậc
    0.06
     마
    0.06
    Act Density 0.001%

    No Known Activations