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

    Neuronpedia

    INDEX
    Explanations

    placebo

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    现代
    -0.07
    עשה
    -0.07
     Kann
    -0.07
    付费
    -0.07
    mul
    -0.07
     Greenville
    -0.07
     finding
    -0.07
     withdraw
    -0.07
    tees
    -0.07
    '",
    -0.07
    POSITIVE LOGITS
    _initialized
    0.07
     enum
    0.07
    福特
    0.07
    쿱
    0.07
    ˤ
    0.06
     Mockito
    0.06
    끕
    0.06
     EAR
    0.06
    _Vector
    0.06
    WindowTitle
    0.06
    Act Density 0.002%

    No Known Activations