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

    Neuronpedia

    INDEX
    Explanations

    dressing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (records
    -0.07
    BAB
    -0.06
     speci
    -0.06
     bowling
    -0.06
    ế
    -0.06
    (fs
    -0.06
    axes
    -0.06
    inking
    -0.06
    aims
    -0.06
     (~(
    -0.06
    POSITIVE LOGITS
    rette
    0.07
     dirt
    0.06
    \Annotation
    0.06
     handgun
    0.06
    ційних
    0.06
    _area
    0.06
     authorization
    0.06
    ستان
    0.06
     acknowledge
    0.06
    ัวร
    0.06
    Act Density 0.007%

    No Known Activations