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

    Neuronpedia

    INDEX
    Explanations

    immediate, first, Recent

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Спо
    0.45
     sickly
    0.45
     пытается
    0.43
    פ
    0.42
    ੋ
    0.42
     ={
    0.42
    РИ
    0.42
     хоче
    0.42
    ారులు
    0.42
    א
    0.41
    POSITIVE LOGITS
     Veterans
    0.48
     বেশ
    0.43
    稳定
    0.43
    kV
    0.40
     Dashboard
    0.40
     Excav
    0.39
    LV
    0.39
     Community
    0.39
     exactly
    0.39
     opener
    0.38
    Act Density 0.010%

    No Known Activations