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

    Neuronpedia

    INDEX
    Explanations

    validation or winning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    a
    0.52
     metam
    0.51
    on
    0.49
     Config
    0.48
     curd
    0.48
     qua
    0.45
     Rash
    0.43
    setOn
    0.43
     ?)
    0.43
     OPD
    0.43
    POSITIVE LOGITS
    ین
    0.50
    стях
    0.50
    ('.',
    0.49
    㽡
    0.49
     robberies
    0.49
     ثبت
    0.48
    ster
    0.48
     minyak
    0.48
     최고의
    0.48
     touring
    0.48
    Act Density 0.000%

    No Known Activations