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

    Neuronpedia

    INDEX
    Explanations

    you don't have to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    tray
    0.41
    ⦕
    0.38
    也能
    0.38
    SuppressLint
    0.37
    可知
    0.36
    pady
    0.35
    狂
    0.35
    يميديا
    0.35
    loadImage
    0.35
    受け
    0.34
    POSITIVE LOGITS
     MK
    0.43
     tai
    0.41
     Accounting
    0.41
     worst
    0.41
    versions
    0.41
    MK
    0.40
     Alleg
    0.40
    िसो
    0.39
    ired
    0.38
     Algorithm
    0.38
    Act Density 0.001%

    No Known Activations