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

    Neuronpedia

    INDEX
    Explanations

    baby and associated terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    the
    1.36
     powied
    1.30
    ו
    1.28
    ਮ
    1.21
    น
    1.16
    ה
    1.16
    ל
    1.16
     the
    1.15
     it
    1.11
    ま
    1.08
    POSITIVE LOGITS
     Baby
    1.21
    েন
    1.13
    很多
    1.05
    ick
    1.04
    ة
    1.00
    y
    0.99
    一些
    0.98
    datei
    0.98
    stoffen
    0.95
    婴儿
    0.94
    Act Density 0.007%

    No Known Activations