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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Nearly
    -0.06
    _two
    -0.06
    _MINUS
    -0.06
    [F
    -0.06
     pint
    -0.06
     colleague
    -0.05
    باح
    -0.05
     median
    -0.05
    .same
    -0.05
     whe
    -0.05
    POSITIVE LOGITS
    .name
    0.08
    Application
    0.07
    submission
    0.07
     scientific
    0.07
    .bootstrap
    0.07
     Hier
    0.07
    -kind
    0.07
     Exist
    0.06
    sunuz
    0.06
    yı
    0.06
    Act Density 0.009%

    No Known Activations