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

    Neuronpedia

    INDEX
    Explanations

    schedule 1:1s with key stakeholders

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Fechar
    0.80
    教程
    0.76
    rtl
    0.72
    ற்காக
    0.71
     समज
    0.69
    Playing
    0.69
     onu
    0.69
    them
    0.68
    Xi
    0.68
    พร้อม
    0.68
    POSITIVE LOGITS
     tramp
    0.83
     fishing
    0.78
     trans
    0.77
     بلو
    0.75
     trance
    0.73
    ImageLayout
    0.73
     LZ
    0.72
     gusts
    0.72
     ut
    0.71
     LOC
    0.70
    Act Density 0.000%

    No Known Activations