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

    Neuronpedia

    INDEX
    Explanations

    names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Leon
    -0.07
     删除
    -0.07
     答
    -0.06
     Resets
    -0.06
     atan
    -0.06
     poured
    -0.06
     간
    -0.06
    ülü
    -0.06
     undone
    -0.06
     told
    -0.06
    POSITIVE LOGITS
    ารถ
    0.07
    ihil
    0.07
    omens
    0.06
     mois
    0.06
    \"",↵
    0.06
    StatusLabel
    0.06
    izzle
    0.06
    _COMPAT
    0.06
    ű
    0.06
    _FOREACH
    0.06
    Act Density 0.001%

    No Known Activations