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

    Neuronpedia

    INDEX
    Explanations

    positive affirmations

    np_acts-logits-general · gemini-2.5-flash-lite

    Wednesday evening

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ла
    0.66
     voet
    0.52
    аз
    0.50
    ле
    0.49
     operand
    0.48
     পাথর
    0.48
     onLoad
    0.46
     tradi
    0.46
    вич
    0.46
     bestand
    0.45
    POSITIVE LOGITS
    nts
    0.70
    ن
    0.59
    ﻦ
    0.57
    راہیم
    0.51
    日子
    0.50
    ार्टम
    0.50
    rime
    0.50
     countertops
    0.50
    𝕥
    0.50
    ɴ
    0.49
    Act Density 0.000%

    No Known Activations