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

    Neuronpedia

    INDEX
    Explanations

    LBM basics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    습니다
    0.74
     erforder
    0.70
    তে
    0.70
    tmpl
    0.64
    où
    0.64
    Jetzt
    0.63
     Blanch
    0.62
    어요
    0.61
    ă
    0.60
     notwend
    0.60
    POSITIVE LOGITS
     PAH
    0.94
     lanthan
    0.88
     aisa
    0.88
     getc
    0.87
    儡
    0.85
    लिये
    0.85
    ﺩ
    0.84
    、​
    0.84
    اما
    0.84
     inim
    0.84
    Act Density 0.002%

    No Known Activations