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

    Neuronpedia

    INDEX
    Explanations

    predicting word continuations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     identifying
    0.27
    Various
    0.27
     Identifying
    0.26
     অন্য
    0.26
     Example
    0.25
    (/*
    0.25
    সপ
    0.25
    κει
    0.25
    ambers
    0.25
    frm
    0.25
    POSITIVE LOGITS
     ransomware
    0.38
     کیسینو
    0.36
     کاسینو
    0.30
     جوسینو
    0.30
     ﷺ
    0.29
     Luffy
    0.28
     Kubernetes
    0.28
     voetbal
    0.28
     سلاټ
    0.27
     Ruto
    0.27
    Act Density 0.237%

    No Known Activations