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

    Neuronpedia

    INDEX
    Explanations

    here and

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     probabilistic
    0.29
     granularity
    0.27
     benutzer
    0.27
     일반적으로
    0.26
    mathemat
    0.26
     computational
    0.25
     Verwendung
    0.25
     metri
    0.24
     explic
    0.24
     ഉപകരണ
    0.24
    POSITIVE LOGITS
    !”
    0.36
    !”.
    0.32
    !”,
    0.29
    !"
    0.29
    !".
    0.28
    !»
    0.27
    !";
    0.27
     sărb
    0.27
     тебя
    0.26
     powiedział
    0.25
    Act Density 2.782%

    No Known Activations