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

    Neuronpedia

    INDEX
    Explanations

    jud

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _venta
    -0.08
    نعم
    -0.08
     ==========
    -0.07
    uiten
    -0.07
     illusions
    -0.07
    -abs
    -0.07
    amber
    -0.07
    ół
    -0.07
     fiberglass
    -0.07
     Cv
    -0.07
    POSITIVE LOGITS
     ITS
    0.07
    REG
    0.07
    ?\
    0.07
     fields
    0.07
    !\
    0.07
    عان
    0.07
     intercepted
    0.07
    ANT
    0.07
    sequential
    0.07
    놧
    0.07
    Act Density 0.002%

    No Known Activations