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

    Neuronpedia

    INDEX
    Explanations

    programming keywords followed by underscore

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ها
    1.02
     Và
    0.96
    ه‌ها
    0.88
     बारे
    0.87
     هایی
    0.86
     Of
    0.84
     festgestellt
    0.84
    हरू
    0.83
    ერს
    0.83
     Jeden
    0.83
    POSITIVE LOGITS
    _
    1.44
    \_
    1.13
    _*
    0.84
    _,
    0.82
    _"
    0.78
     sede
    0.77
    _$
    0.76
    ＿
    0.75
     ci
    0.75
     gosto
    0.73
    Act Density 0.155%

    No Known Activations