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

    Neuronpedia

    INDEX
    Explanations

    iddle

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dragged
    -0.08
    venue
    -0.07
    ategori
    -0.07
     Modules
    -0.06
     cloud
    -0.06
    カル
    -0.06
     plummet
    -0.06
    Student
    -0.06
     Alphabet
    -0.06
     �
    -0.06
    POSITIVE LOGITS
     institutes
    0.07
     EMPTY
    0.06
     kişiler
    0.06
    ักษณะ
    0.06
    _legal
    0.06
     bidi
    0.06
    awaii
    0.06
    iap
    0.06
    ResponseBody
    0.06
    ll
    0.06
    Act Density 0.001%

    No Known Activations