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

    Neuronpedia

    INDEX
    Explanations

    code loops and arrays

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    または
    0.74
    الص
    0.73
     சுத்த
    0.71
    付け
    0.69
    போ
    0.68
     sheer
    0.65
    ឬ
    0.65
    რი
    0.64
    ஜீ
    0.64
     Ć
    0.62
    POSITIVE LOGITS
    र्यंत
    0.85
     playthrough
    0.82
     dependences
    0.80
     fractures
    0.78
     протяжении
    0.73
    ۋ
    0.72
     সাত
    0.72
     நவ
    0.72
    க்குள்
    0.70
    delà
    0.70
    Act Density 0.016%

    No Known Activations