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

    Neuronpedia

    INDEX
    Explanations

    whodunnit

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    хо
    0.42
    Rush
    0.39
     letra
    0.38
    늡
    0.38
     Rush
    0.38
     rushing
    0.37
     Traverse
    0.37
     asm
    0.37
     Cholesterol
    0.36
    ো
    0.36
    POSITIVE LOGITS
    伦
    0.41
    탔
    0.41
    匠
    0.39
    ците
    0.39
     entirely
    0.39
     १८
    0.38
    oten
    0.38
    chand
    0.37
     dimiliki
    0.37
    ⴹ
    0.37
    Act Density 0.000%

    No Known Activations