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

    Neuronpedia

    INDEX
    Explanations

    Introduction to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    isBlank
    0.37
    igraf
    0.37
    isIn
    0.36
    acija
    0.36
    сування
    0.36
     doš
    0.35
     szem
    0.35
    itta
    0.35
    aikh
    0.35
     oko
    0.34
    POSITIVE LOGITS
    큘
    0.41
    任意の
    0.40
     thy
    0.38
    の結果
    0.38
    楍
    0.38
    യ്ക്ക്
    0.38
     আপডেট
    0.37
    悱
    0.37
    роят
    0.37
     இதற்கு
    0.37
    Act Density 0.001%

    No Known Activations