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

    Neuronpedia

    INDEX
    Explanations

    @

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     lock
    -0.07
    Share
    -0.07
    #↵
    -0.07
    "/>
↵
    -0.07
    	BOOL
    -0.07
    celona
    -0.07
    -forward
    -0.06
     groupName
    -0.06
     //'
    -0.06
    ++;
↵
    -0.06
    POSITIVE LOGITS
    _ISO
    0.07
    .Health
    0.06
    (times
    0.06
    aceut
    0.06
     zel
    0.06
    _hom
    0.06
    _MET
    0.06
     Kore
    0.06
    _od
    0.06
    roulette
    0.06
    Act Density 0.003%

    No Known Activations