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

    Neuronpedia

    INDEX
    Explanations

    a and similar characters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    CHANT
    0.79
     activism
    0.78
     Algon
    0.77
     انھیں
    0.77
     mew
    0.76
     Марафон
    0.75
    ர்த
    0.75
     می‌باشد
    0.74
     Alcan
    0.73
     optimality
    0.73
    POSITIVE LOGITS
    a
    0.89
     dona
    0.82
     ua
    0.78
     loa
    0.74
    ia
    0.74
     ia
    0.73
     বিদ
    0.72
     cara
    0.71
    Ao
    0.71
    ea
    0.70
    Act Density 0.003%

    No Known Activations