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

    Neuronpedia

    INDEX
    Explanations

    domain endings /

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     terbaru
    0.27
     náklady
    0.26
    gebras
    0.26
     dommages
    0.25
    诅
    0.25
     perbedaan
    0.24
     അനുവദ
    0.24
    ="/"
    0.24
    aadhar
    0.24
    €
    0.24
    POSITIVE LOGITS
    pages
    0.29
     category
    0.28
    category
    0.27
     rubrique
    0.26
    /
    0.26
     our
    0.26
    quick
    0.25
     Category
    0.25
    G
    0.25
    Re
    0.25
    Act Density 0.009%

    No Known Activations