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

    Neuronpedia

    INDEX
    Explanations

    form verification

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    sav
    -0.08
     stamp
    -0.07
    .dart
    -0.07
    (mean
    -0.07
    缺乏
    -0.07
    깨
    -0.07
    arnings
    -0.07
     Swift
    -0.07
    _EDIT
    -0.07
     $('#
    -0.07
    POSITIVE LOGITS
     A
    0.07
     mitigate
    0.07
    ał
    0.06
    ignal
    0.06
     UserController
    0.06
    apult
    0.06
    0.06
     Session
    0.06
     rollers
    0.06
    ać
    0.06
    Act Density 0.008%

    No Known Activations