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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     מקום
    -0.07
    uming
    -0.07
    䴗
    -0.07
    מקום
    -0.07
    _CTX
    -0.06
    隐瞒
    -0.06
    	mc
    -0.06
    פלא
    -0.06
    iamo
    -0.06
    utch
    -0.06
    POSITIVE LOGITS
    Social
    0.08
     "{$
    0.07
    rid
    0.07
     splits
    0.07
    峗
    0.07
    肸
    0.07
     dissoci
    0.07
    *</
    0.07
    ovid
    0.07
    𫍲
    0.07
    Act Density 0.001%

    No Known Activations