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

    Neuronpedia

    INDEX
    Explanations

    refusal

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -self
    -0.07
     outdated
    -0.07
     Garrison
    -0.07
    _HandleTypeDef
    -0.06
    124
    -0.06
     CAS
    -0.06
    .owner
    -0.06
    至
    -0.06
    �
    -0.06
    TXT
    -0.06
    POSITIVE LOGITS
    敵
    0.06
    	Message
    0.06
    (Activity
    0.06
     lời
    0.06
     slož
    0.06
    のか
    0.06
     Phantom
    0.06
    iect
    0.06
    elerinin
    0.06
    ячи
    0.06
    Act Density 0.013%

    No Known Activations