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

    Neuronpedia

    INDEX
    Explanations

    program Files

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    েন্ট
    0.73
     太
    0.69
    nestjs
    0.64
     Schofield
    0.63
    cluding
    0.62
    nilai
    0.62
     reds
    0.62
     Champion
    0.61
    天
    0.60
     supporters
    0.60
    POSITIVE LOGITS
    Counter
    1.02
     Counter
    0.99
     counter
    0.89
    izarra
    0.89
    カウン
    0.88
    counter
    0.88
     широкий
    0.86
    ziert
    0.86
     पारंपरिक
    0.83
     Flow
    0.82
    Act Density 0.011%

    No Known Activations