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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    HttpStatus
    -0.07
     生命周期函数
    -0.06
    птом
    -0.06
     Screens
    -0.06
     Lesser
    -0.06
    Milliseconds
    -0.06
     gracious
    -0.06
    정을
    -0.06
    mişti
    -0.06
     Demonstr
    -0.06
    POSITIVE LOGITS
    atories
    0.08
     composing
    0.07
    afil
    0.07
     convey
    0.06
    uv
    0.06
     пам
    0.06
     Jersey
    0.06
    梯
    0.06
     Blade
    0.06
     connects
    0.06
    Act Density 0.005%

    No Known Activations