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

    Neuronpedia

    INDEX
    Explanations

    Non-English language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     arresting
    -0.06
     Universities
    -0.06
    807
    -0.06
     آسی
    -0.06
     Drugs
    -0.06
    ots
    -0.06
     crime
    -0.06
    sip
    -0.06
    791
    -0.06
    成為
    -0.06
    POSITIVE LOGITS
    .ph
    0.07
     �
    0.07
    양
    0.07
    _notify
    0.07
     พ
    0.07
    PTR
    0.07
     �
    0.07
    .Cont
    0.06
    قات
    0.06
     तत
    0.06
    Act Density 0.128%

    No Known Activations