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

    Neuronpedia

    INDEX
    Explanations

    code repositories

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Delete
    -0.07
     Continuous
    -0.07
     Національ
    -0.07
    .Shapes
    -0.06
     blanc
    -0.06
     Ist
    -0.06
    -e
    -0.06
     خو
    -0.06
    QRSTUVWXYZ
    -0.06
    UGC
    -0.06
    POSITIVE LOGITS
    ětí
    0.07
    کتر
    0.06
     sore
    0.06
    .ag
    0.06
    _;↵
    0.06
     subtype
    0.06
    aic
    0.06
    oons
    0.06
    .visualization
    0.06
     sher
    0.06
    Act Density 0.002%

    No Known Activations