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

    Neuronpedia

    INDEX
    Explanations

    Letter sign-offs

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     goggles
    -0.07
    ген
    -0.07
    elix
    -0.07
    gal
    -0.07
     Gets
    -0.07
    gov
    -0.07
    encia
    -0.07
    🚌
    -0.07
    まして
    -0.06
    Josh
    -0.06
    POSITIVE LOGITS
    ไต
    0.08
    cript
    0.07
     cru
    0.07
    溲
    0.07
    耤
    0.07
    (b
    0.07
     whipping
    0.07
    [first
    0.07
     trab
    0.06
    hashed
    0.06
    Act Density 0.016%

    No Known Activations