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

    Neuronpedia

    INDEX
    Explanations

    within

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    etat
    -0.07
     Население
    -0.06
     줄
    -0.06
    _rb
    -0.06
    __',
    -0.06
     ndarray
    -0.06
     snakes
    -0.06
    迷
    -0.06
    eto
    -0.06
     folding
    -0.06
    POSITIVE LOGITS
     within
    0.08
    Insp
    0.07
    .Inter
    0.06
    classification
    0.06
     filmmakers
    0.06
     Generation
    0.06
    LabelText
    0.06
    overview
    0.06
    ruž
    0.06
    within
    0.06
    Act Density 0.005%

    No Known Activations