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

    Neuronpedia

    INDEX
    Explanations

    Google

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    xbd
    -0.08
     unveil
    -0.07
     serves
    -0.07
    adal
    -0.07
    	stack
    -0.07
     Reef
    -0.07
     lavoro
    -0.06
    ünd
    -0.06
    ᅵ
    -0.06
     sunday
    -0.06
    POSITIVE LOGITS
    사업
    0.07
     climbers
    0.07
     locales
    0.07
    _AUDIO
    0.07
     oficial
    0.07
    减速
    0.07
     котор
    0.07
    Mode
    0.06
    nehmen
    0.06
     Memo
    0.06
    Act Density 0.009%

    No Known Activations