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

    Neuronpedia

    INDEX
    Explanations

    morning time descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ক
    1.62
    А
    1.61
    的话
    1.59
    Não
    1.54
    ن
    1.51
    is
    1.47
    ème
    1.45
    ন
    1.45
     Consultado
    1.44
    mangle
    1.44
    POSITIVE LOGITS
    ో
    1.88
    noon
    1.84
    ﭘ
    1.65
    ne
    1.57
    킵
    1.55
    юнча
    1.53
     قریب
    1.53
    씩
    1.48
     cedo
    1.47
    redients
    1.46
    Act Density 0.050%

    No Known Activations