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

    Neuronpedia

    INDEX
    Explanations

    Americans

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ५
    -0.07
    [NUM
    -0.07
     немає
    -0.06
     bigger
    -0.06
    _INTERRUPT
    -0.06
     extent
    -0.06
    ."↵↵
    -0.06
     likes
    -0.06
     reconcile
    -0.06
     SHIFT
    -0.06
    POSITIVE LOGITS
    irtual
    0.06
     Med
    0.06
    -service
    0.06
    IFEST
    0.06
     Gn
    0.06
    Warn
    0.06
    гар
    0.06
     Murder
    0.06
    ifornia
    0.06
    (arg
    0.06
    Act Density 0.000%

    No Known Activations