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

    Neuronpedia

    INDEX
    Explanations

    summarize

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     fotografi
    0.79
    𝚍
    0.76
    კო
    0.75
     enfermed
    0.75
    EndZ
    0.73
     AstraZeneca
    0.73
     arugula
    0.73
    ково
    0.72
    қо
    0.71
     একদিন
    0.71
    POSITIVE LOGITS
    ייה
    0.88
    ísticas
    0.76
    ister
    0.75
    ikan
    0.75
    istics
    0.74
    ste
    0.72
    tes
    0.72
    יית
    0.71
    tect
    0.69
    یوں
    0.69
    Act Density 0.002%

    No Known Activations