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

    Neuronpedia

    INDEX
    Explanations

    stick

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    {{$
    -0.08
    Auto
    -0.08
    ospital
    -0.07
     raids
    -0.07
     underworld
    -0.07
    örper
    -0.06
    夏日
    -0.06
    佺
    -0.06
     באותה
    -0.06
    assel
    -0.06
    POSITIVE LOGITS
    粘
    0.08
    فيل
    0.07
    .WinForms
    0.07
    _TERMIN
    0.07
    TransparentColor
    0.06
     PI
    0.06
    條
    0.06
     żeby
    0.06
    Wall
    0.06
    IAM
    0.06
    Act Density 0.011%

    No Known Activations