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

    Neuronpedia

    INDEX
    Explanations

    towel

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     گوش
    -0.07
    (cd
    -0.07
     scand
    -0.07
     CS
    -0.06
     Gateway
    -0.06
    _boot
    -0.06
     Auto
    -0.06
     Jude
    -0.06
     gold
    -0.06
     Gold
    -0.06
    POSITIVE LOGITS
     towel
    0.09
     tịch
    0.06
    悪
    0.06
     continuar
    0.06
    analyze
    0.06
    .Error
    0.06
    診
    0.06
     towels
    0.06
     także
    0.06
    .setError
    0.06
    Act Density 0.010%

    No Known Activations