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

    Neuronpedia

    INDEX
    Explanations

    list separators and links

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    …
    0.44
     but
    0.42
    ump
    0.41
     th
    0.41
    ă
    0.41
    ua
    0.40
     wasn
    0.39
    .
    0.39
    nn
    0.38
    。
    0.38
    POSITIVE LOGITS
     Technologien
    0.45
     فعال
    0.44
     കമ്മി
    0.43
     Werte
    0.43
     Lösungen
    0.43
    𒋗
    0.43
    راہیم
    0.42
     बैंड
    0.42
    ेंसेस
    0.42
     transforme
    0.42
    Act Density 0.108%

    No Known Activations