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

    Neuronpedia

    INDEX
    Explanations

    code commands and explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0.87
    ادی
    0.86
    Iso
    0.83
     साइन
    0.81
    Tyr
    0.80
    庤
    0.80
     eisen
    0.79
     Iz
    0.78
     फिगर
    0.77
    oling
    0.76
    POSITIVE LOGITS
    গম
    0.65
     महासभा
    0.60
     Roadmap
    0.58
     roadmap
    0.56
    ::
    0.55
    かな
    0.55
    ค
    0.54
    occo
    0.52
    ্লাস
    0.52
    []
    0.52
    Act Density 0.064%

    No Known Activations