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

    Neuronpedia

    INDEX
    Explanations

    praise

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     IH
    -0.07
     qp
    -0.06
     Enemies
    -0.06
     enough
    -0.06
     banquet
    -0.06
    ロ
    -0.06
     camps
    -0.06
    ullivan
    -0.06
     strr
    -0.06
    按钮
    -0.06
    POSITIVE LOGITS
    ARIANT
    0.07
    روت
    0.07
    _ASSUME
    0.07
     SOLUTION
    0.07
    _SESSION
    0.06
    REEN
    0.06
    aginator
    0.06
    CONTACT
    0.06
     Link
    0.06
    NAME
    0.06
    Act Density 0.014%

    No Known Activations