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

    Neuronpedia

    INDEX
    Explanations

    code or query context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    歇
    0.41
     StringBuilder
    0.39
    のだが
    0.38
    !!!!!!!!!!!!!!!!
    0.38
     divergents
    0.37
    彳
    0.37
    ষণের
    0.37
     Stretch
    0.36
     IAEA
    0.36
    Interpret
    0.36
    POSITIVE LOGITS
    ?
    0.73
    ？
    0.70
    ؟
    0.66
    ?>
    0.63
    ？”
    0.60
    ?$
    0.58
    ?]
    0.55
     ?
    0.54
     ؟
    0.53
    ？」
    0.52
    Act Density 0.000%

    No Known Activations