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

    Neuronpedia

    INDEX
    Explanations

    comparing and differentiating options

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    生产
    0.52
    这个
    0.47
    Parsing
    0.47
    㭜
    0.47
    初始化
    0.46
     Severity
    0.46
    ገ
    0.46
    Severity
    0.45
    それが
    0.45
    尟
    0.45
    POSITIVE LOGITS
     eased
    0.46
    ında
    0.45
     whatnot
    0.45
     comfortably
    0.44
     fluctu
    0.43
     satisfactory
    0.43
     vt
    0.43
    television
    0.43
     wept
    0.43
     television
    0.42
    Act Density 0.005%

    No Known Activations