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

    Neuronpedia

    INDEX
    Explanations

    "don't" followed by verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ים
    0.52
     maaaring
    0.39
     archival
    0.37
     pluripotent
    0.36
     glist
    0.36
     rafters
    0.34
     kanamycin
    0.34
     zipped
    0.33
     سيكون
    0.33
    s
    0.33
    POSITIVE LOGITS
    н
    0.50
    \
    0.44
    ン
    0.42
    ن
    0.41
    л
    0.38
    n
    0.36
    t
    0.35
     on
    0.34
     of
    0.32
    of
    0.31
    Act Density 0.393%

    No Known Activations