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

    Neuronpedia

    INDEX
    Explanations

    research findings and data

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     groe
    0.55
     de
    0.52
     अद्भ
    0.52
     paling
    0.51
    у
    0.50
     แต่
    0.49
     CTV
    0.49
     tuttavia
    0.49
    f
    0.48
     Tele
    0.48
    POSITIVE LOGITS
    തെന്നും
    0.43
    Subject
    0.41
     জন্যও
    0.40
    ocurrency
    0.39
    OrElse
    0.39
     куда
    0.38
    Respondent
    0.38
    刳
    0.38
    تان
    0.38
     अनुरोध
    0.38
    Act Density 0.013%

    No Known Activations