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

    Neuronpedia

    INDEX
    Explanations

    Abbreviations/References

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ucking
    -0.08
    ξ
    -0.07
    ventas
    -0.07
    acos
    -0.07
     RI
    -0.07
    打电话
    -0.06
    Constraints
    -0.06
    ibre
    -0.06
    笑笑
    -0.06
     chuck
    -0.06
    POSITIVE LOGITS
    正在
    0.07
    Assembler
    0.07
    ')}↵
    0.07
     aroused
    0.07
    _equalTo
    0.07
     awakeFromNib
    0.07
     있었
    0.07
    任意
    0.07
     disreg
    0.07
    ...↵↵↵↵↵↵
    0.07
    Act Density 0.158%

    No Known Activations