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

    Neuronpedia

    INDEX
    Explanations

    numpy

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     plugin
    0.86
     Plugin
    0.84
    Plugin
    0.82
     incluida
    0.78
    olata
    0.76
    插件
    0.75
    lol
    0.75
     incluido
    0.75
     plugins
    0.74
     incluidas
    0.73
    POSITIVE LOGITS
     Sign
    0.63
     ගැනීම
    0.62
    ர்த்த
    0.60
     ste
    0.60
    เพ
    0.60
     Nam
    0.60
     Lift
    0.59
     अमन
    0.58
     व्यापारी
    0.57
     бизнес
    0.57
    Act Density 0.001%

    No Known Activations