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

    Neuronpedia

    INDEX
    Explanations

    technical terms and code

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     حسين
    0.54
    zyloxy
    0.53
     nominations
    0.52
    MakeRange
    0.52
     nomination
    0.51
    后缀
    0.50
     conic
    0.50
     coni
    0.50
    外部リンク
    0.50
    MakeRect
    0.49
    POSITIVE LOGITS
    劏
    0.77
     Whale
    0.62
    whale
    0.60
    YC
    0.57
     கடல்
    0.56
    inkle
    0.54
    حدد
    0.54
    determine
    0.54
    殿
    0.53
    মী
    0.53
    Act Density 0.002%

    No Known Activations