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

    Neuronpedia

    INDEX
    Explanations

    dates and numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     su
    0.63
     inherent
    0.61
     part
    0.61
     sign
    0.61
     rep
    0.61
     in
    0.58
     virtual
    0.58
     no
    0.58
     up
    0.58
     fine
    0.57
    POSITIVE LOGITS
     страны
    0.77
     количество
    0.76
    4
    0.75
     снижение
    0.74
    ीडियो
    0.74
    вали
    0.73
    количество
    0.72
    <unused114>
    0.71
    ümüş
    0.71
     нефте
    0.71
    Act Density 0.040%

    No Known Activations