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

    Neuronpedia

    INDEX
    Explanations

    somehow related

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Malcolm
    0.45
     multiSelectList
    0.44
    នៅលើ
    0.43
     মিলি
    0.43
     ਆਪਣ
    0.43
     Herbs
    0.42
     Idani
    0.42
     Referenced
    0.41
     Malibu
    0.40
    扡
    0.40
    POSITIVE LOGITS
    توان
    0.48
     graças
    0.47
    ص
    0.46
    نتی
    0.46
    鲜
    0.46
     aseg
    0.45
    र्घ
    0.44
    فر
    0.43
     compressors
    0.43
    ερ
    0.43
    Act Density 0.001%

    No Known Activations