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

    Neuronpedia

    INDEX
    Explanations

    built

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ADS
    -0.06
    '],
    -0.06
     deposits
    -0.06
    	stack
    -0.06
    _store
    -0.06
     balls
    -0.06
     tremend
    -0.06
    _version
    -0.06
    асс
    -0.06
    ätze
    -0.06
    POSITIVE LOGITS
     هم
    0.07
     built
    0.07
    手に
    0.06
    .den
    0.06
     Cust
    0.06
    .utc
    0.06
    ，一
    0.06
     onBackPressed
    0.06
     dug
    0.06
    自
    0.06
    Act Density 0.009%

    No Known Activations