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

    Neuronpedia

    INDEX
    Explanations

    talks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ft
    -0.07
     jd
    -0.07
    602
    -0.07
     WC
    -0.07
     مض
    -0.07
     SMTP
    -0.07
     BJ
    -0.07
     پیر
    -0.06
     pir
    -0.06
    MS
    -0.06
    POSITIVE LOGITS
    ']*
    0.07
    でも
    0.06
    Creators
    0.06
    ?;↵↵
    0.06
    Rad
    0.06
     Then
    0.06
    LAB
    0.06
    .Must
    0.06
     vài
    0.06
     DataFrame
    0.06
    Act Density 0.283%

    No Known Activations