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

    Neuronpedia

    INDEX
    Explanations

    code punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    шили
    -0.07
    udic
    -0.07
    operation
    -0.06
     Movies
    -0.06
    agog
    -0.06
     Momentum
    -0.06
    MH
    -0.06
     offense
    -0.06
     appart
    -0.06
     license
    -0.06
    POSITIVE LOGITS
     الإسلام
    0.07
     이동합니다
    0.07
     NotificationCenter
    0.07
    (coll
    0.06
     सफ
    0.06
    ApiKey
    0.06
    伸
    0.06
    �
    0.06
     raising
    0.06
     Delay
    0.06
    Act Density 0.005%

    No Known Activations