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

    Neuronpedia

    INDEX
    Explanations

    considering sales

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     vattati
    0.38
    ovati
    0.38
    憸
    0.36
    вить
    0.34
     zg
    0.34
     throttling
    0.34
    vg
    0.33
     rechercher
    0.33
     progres
    0.33
     THRO
    0.33
    POSITIVE LOGITS
    COLUMN
    0.41
     Paperback
    0.40
     Reprinted
    0.40
    oría
    0.40
    Chapter
    0.38
     Parce
    0.38
    PATTERN
    0.34
    ková
    0.34
    笺
    0.34
     دیر
    0.33
    Act Density 0.001%

    No Known Activations