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

    Neuronpedia

    INDEX
    Explanations

    between

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     $+\
    0.54
    marginY
    0.53
    persons
    0.52
    ňuje
    0.52
    成立于
    0.52
    বৃদ্ধি
    0.52
    𝓼
    0.52
     personnes
    0.51
    ův
    0.51
    댔
    0.51
    POSITIVE LOGITS
     '
    0.68
    曝光
    0.65
     antara
    0.63
     between
    0.60
     politically
    0.60
     بين
    0.58
     میان
    0.58
     powerfully
    0.58
     beside
    0.56
     level
    0.55
    Act Density 0.000%

    No Known Activations