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

    Neuronpedia

    INDEX
    Explanations

    programming variable and code indicators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    𝒋
    0.84
    Р
    0.84
    ी
    0.82
     autre
    0.81
    ㄼ
    0.78
     odkazy
    0.77
     बीटल
    0.76
    অর্থাৎ
    0.76
     foe
    0.76
    б
    0.75
    POSITIVE LOGITS
    t
    0.80
    matic
    0.74
    ទទួលបាន
    0.74
    0.74
    ﻪ
    0.73
    তা
    0.72
     newly
    0.69
    യും
    0.69
     принад
    0.67
    ாவின்
    0.67
    Act Density 0.041%

    No Known Activations