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

    Neuronpedia

    INDEX
    Explanations

    add to cart or plugin

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    𝑓
    0.86
    )$
    0.84
    ){
    0.84
     கூறினார்
    0.80
    ){//
    0.78
    𝑎
    0.77
    です
    0.77
    𝑠
    0.76
    ()=>{
    0.75
    ان
    0.73
    POSITIVE LOGITS
    ﻘ
    0.91
    -
    0.80
    CTION
    0.75
     оставля
    0.75
    วัสดี
    0.74
     وعلى
    0.73
     menstruation
    0.72
    ﻌ
    0.71
     этапе
    0.71
    𝓽
    0.70
    Act Density 0.000%

    No Known Activations