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

    Neuronpedia

    INDEX
    Explanations

    modern values

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Два
    0.40
    Qty
    0.39
    𝐢
    0.38
    Seconds
    0.38
     për
    0.37
    jším
    0.37
     کو
    0.37
     qRT
    0.36
    Кла
    0.36
     Spannung
    0.35
    POSITIVE LOGITS
     sciences
    0.39
     linguistic
    0.37
    formerly
    0.37
    el
    0.36
    R
    0.36
    0
    0.36
     standpoint
    0.35
    w
    0.34
    5
    0.34
     lexical
    0.33
    Act Density 0.000%

    No Known Activations