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

    Neuronpedia

    INDEX
    Explanations

    figuring out what

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ד
    0.53
    фа
    0.49
    ה
    0.49
    サンプル
    0.48
    タ
    0.46
    רי
    0.46
    ra
    0.46
    то
    0.46
    מ
    0.46
    ジ
    0.46
    POSITIVE LOGITS
    நிலை
    0.46
    uland
    0.46
    ave
    0.43
     TextInputLayout
    0.43
    Ning
    0.43
     căn
    0.42
    iven
    0.41
    aye
    0.41
     indie
    0.41
    ployment
    0.40
    Act Density 0.000%

    No Known Activations