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

    Neuronpedia

    INDEX
    Explanations

    **

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Starts
    -0.07
    �
    -0.06
     Wenger
    -0.06
    _sh
    -0.06
     Hundred
    -0.06
    '";↵
    -0.06
     exhausting
    -0.06
     щ
    -0.06
    _AUD
    -0.06
    ru
    -0.06
    POSITIVE LOGITS
    sans
    0.07
    lj
    0.07
     CGPoint
    0.07
     smoothing
    0.07
     te
    0.06
    امی
    0.06
     γεν
    0.06
    ิส
    0.06
     širo
    0.06
    　　 　 　
    0.06
    Act Density 0.012%

    No Known Activations