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

    Neuronpedia

    INDEX
    Explanations

    doesn't

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    y
    -2.34
     see
    -2.27
    .”
    -2.22
    谖
    -2.20
    ia
    -2.19
    ITHUB
    -2.19
    してくれた
    -2.17
     didn
    -2.17
    ına
    -2.13
     you
    -2.09
    POSITIVE LOGITS
    Doesn
    2.39
    doesn
    2.33
    '
    2.28
    拶
    2.16
     Doesn
    2.11
     stär
    2.02
     bekan
    2.00
    Does
    1.84
    ),
    1.80
    锒
    1.74
    Act Density 0.015%

    No Known Activations