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

    Neuronpedia

    INDEX
    Explanations

    checked ignoring, lauded by

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    이
    0.50
    ia
    0.46
    imetype
    0.44
    𝚞
    0.44
    _
    0.43
    compose
    0.43
     rejuvenate
    0.43
    im
    0.40
    jo
    0.40
    ái
    0.40
    POSITIVE LOGITS
    婜
    0.49
    㹂
    0.47
    であれば
    0.46
    רים
    0.46
    সম্পাদকীয়
    0.44
     Performs
    0.44
    Performing
    0.43
    倹
    0.43
     Nou
    0.43
    لمان
    0.43
    Act Density 0.003%

    No Known Activations