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

    Neuronpedia

    INDEX
    Explanations

    import

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    큦
    -0.08
    щи
    -0.08
    Add
    -0.07
    Attr
    -0.07
     бумаг
    -0.07
     декабря
    -0.06
     구성
    -0.06
    ˆ
    -0.06
    分布式
    -0.06
    ꇗ
    -0.06
    POSITIVE LOGITS
    Gary
    0.08
     horrifying
    0.07
    _NEG
    0.07
    _ra
    0.07
     вал
    0.07
    oxic
    0.07
    ONTAL
    0.07
    -made
    0.07
     sabot
    0.07
    assed
    0.07
    Act Density 0.006%

    No Known Activations