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

    Neuronpedia

    INDEX
    Explanations

    key

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    965
    -0.07
    .NET
    -0.07
    include
    -0.07
    HDR
    -0.06
     criticism
    -0.06
    command
    -0.06
    043
    -0.06
    _malloc
    -0.06
    62
    -0.06
     WINDOWS
    -0.06
    POSITIVE LOGITS
     disen
    0.07
     warped
    0.07
    _EMPTY
    0.07
    еріг
    0.06
    _threshold
    0.06
    овж
    0.06
    _throw
    0.06
    /vue
    0.06
    stateProvider
    0.06
     المس
    0.06
    Act Density 0.102%

    No Known Activations