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

    Neuronpedia

    INDEX
    Explanations

    Markdown list item markers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Azul
    0.78
    imo
    0.69
     ไอ
    0.68
     Diret
    0.67
     blau
    0.65
    IMO
    0.63
     azules
    0.63
    BLUE
    0.63
     Auer
    0.62
     passive
    0.62
    POSITIVE LOGITS
    িদ
    0.67
    rients
    0.64
     Kirchen
    0.60
    riting
    0.60
    ਿਰ
    0.56
    ሂ
    0.55
     लगाएं
    0.54
     Ginkuhà
    0.53
    line
    0.53
     ре
    0.52
    Act Density 0.090%

    No Known Activations