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

    Neuronpedia

    INDEX
    Explanations

    non-english greetings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pudd
    2.52
    ية
    2.45
    ो
    2.43
    ০০
    2.40
    σια
    2.34
    HING
    2.34
    ००
    2.25
    𝓉
    2.25
    ONE
    2.23
    जरीवाल
    2.21
    POSITIVE LOGITS
    क
    2.16
     例文帳に追加
    2.15
    ே
    2.11
    ب
    2.04
     reap
    2.02
    LOGGER
    1.98
    علم
    1.94
    u
    1.93
     "../../
    1.87
    μος
    1.86
    Act Density 0.000%

    No Known Activations