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

    Neuronpedia

    INDEX
    Explanations

    decided

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Rich
    -0.07
     Hicks
    -0.07
    istros
    -0.06
    _dialog
    -0.06
     obstruction
    -0.06
     свойства
    -0.06
     звіт
    -0.06
    pherical
    -0.06
     Kling
    -0.06
    stras
    -0.06
    POSITIVE LOGITS
     decided
    0.10
     Ended
    0.07
     ended
    0.07
    roups
    0.07
    added
    0.07
    du
    0.07
     figured
    0.07
    Resolved
    0.07
    videos
    0.07
    ARED
    0.07
    Act Density 0.017%

    No Known Activations