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

    Neuronpedia

    INDEX
    Explanations

    specific nouns and terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Funktionen
    0.27
     Eine
    0.27
     Über
    0.26
     Astrid
    0.25
     Draco
    0.25
     Peut
    0.25
     Eigent
    0.25
     Leia
    0.24
     Tammy
    0.24
     Benutz
    0.24
    POSITIVE LOGITS
    PORT
    0.25
    IDENT
    0.25
    ETTE
    0.24
    ନ୍ଦ
    0.24
    ON
    0.23
    olni
    0.22
    。
    0.22
    LIMIT
    0.22
    ю
    0.22
    ERO
    0.22
    Act Density 2.798%

    No Known Activations