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

    Neuronpedia

    INDEX
    Explanations

    overhaul

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ни
    0.76
    ний
    0.75
     ธ
    0.73
    k
    0.73
    ENN
    0.71
    RA
    0.70
    IST
    0.69
     开始
    0.69
     กลับ
    0.67
     ต้อง
    0.64
    POSITIVE LOGITS
     overhaul
    1.40
     overhauled
    1.21
    <0x80>
    0.93
    ق
    0.81
     éd
    0.80
    0
    0.75
     attaqu
    0.73
     at
    0.73
    يب
    0.72
     établ
    0.71
    Act Density 0.001%

    No Known Activations