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

    Neuronpedia

    INDEX
    Explanations

    quotes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     restrict
    -0.07
    ınıf
    -0.07
    _sql
    -0.07
     institute
    -0.06
    '=>$_
    -0.06
     gentleman
    -0.06
    �
    -0.06
    说明
    -0.06
     Somerset
    -0.06
     relation
    -0.06
    POSITIVE LOGITS
    ót
    0.07
     `-
    0.07
     `<
    0.06
     `'
    0.06
    (`<
    0.06
     sữa
    0.06
    Subsystem
    0.06
     `/
    0.06
    812
    0.06
     अम
    0.06
    Act Density 0.007%

    No Known Activations