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

    Neuronpedia

    INDEX
    Explanations

    lists

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .scene
    -0.07
    .Infrastructure
    -0.07
     Avengers
    -0.06
    Animated
    -0.06
    ्ब
    -0.06
     člověka
    -0.06
    WillDisappear
    -0.06
    ]->
    -0.06
    ██
    -0.06
    ,strlen
    -0.06
    POSITIVE LOGITS
    feit
    0.07
     keypad
    0.06
    ,Yes
    0.06
    альні
    0.06
     此
    0.06
     sexism
    0.06
     Leslie
    0.06
     LOW
    0.06
    _noise
    0.06
    جن
    0.06
    Act Density 0.000%

    No Known Activations