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

    Neuronpedia

    INDEX
    Explanations

    �

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     SHIFT
    -0.07
     Calendar
    -0.06
    \.
    -0.06
     grounded
    -0.06
    .sensor
    -0.06
    ир
    -0.06
     back
    -0.06
     STYLE
    -0.06
    _DIRECTION
    -0.06
     за
    -0.06
    POSITIVE LOGITS
    obody
    0.07
    finding
    0.07
    šli
    0.07
     sexism
    0.07
    ikki
    0.07
    عم
    0.06
     �
    0.06
    _genes
    0.06
     tener
    0.06
    _tF
    0.06
    Act Density 0.001%

    No Known Activations