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

    Neuronpedia

    INDEX
    Explanations

    personalized approach

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     tree
    0.42
    ninger
    0.39
     মিডিয়ায়
    0.39
    burger
    0.38
    tree
    0.38
    Poland
    0.37
    Ring
    0.37
     treason
    0.37
     TREE
    0.37
     fere
    0.36
    POSITIVE LOGITS
    👏
    0.42
    <0xF1>
    0.38
    क्षिप्त
    0.38
    lela
    0.38
    ランク
    0.38
    ۰۰
    0.37
     Malcolm
    0.37
    被迫
    0.37
    સાર
    0.36
     rokov
    0.36
    Act Density 0.000%

    No Known Activations