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

    Neuronpedia

    INDEX
    Explanations

    people's first and last names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
      
    1.04
    0.96
    ,
    0.88
     (
    0.84
     a
    0.84
    .
    0.79
    ↵
    0.79
    /
    0.78
     not
    0.76
     the
    0.75
    POSITIVE LOGITS
    <unused1207>
    1.11
    chyné
    1.11
    oniazid
    1.10
    <unused1893>
    1.06
    ufieurs
    1.06
    <unused2070>
    1.05
    arrerol
    1.04
    <unused1106>
    1.04
    <unused1092>
    1.04
    <unused1759>
    1.03
    Act Density 0.025%

    No Known Activations