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

    Neuronpedia

    INDEX
    Explanations

    hosted services

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    as
    0.58
    s
    0.58
    Ca
    0.56
    res
    0.53
    et
    0.52
    es
    0.51
    mo
    0.51
    en
    0.49
    on
    0.48
    insert
    0.48
    POSITIVE LOGITS
     disrupts
    0.55
    lular
    0.51
     κάν
    0.51
     niż
    0.50
    чок
    0.50
    ="/"
    0.50
     devastation
    0.49
     ഹിന്ദ
    0.49
     atrophy
    0.49
     llrp
    0.49
    Act Density 0.000%

    No Known Activations