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

    Neuronpedia

    INDEX
    Explanations

    hands in something

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Ms
    0.45
     fieldContext
    0.45
    ρος
    0.44
     FURN
    0.43
     PLN
    0.42
     Victims
    0.41
    蟎
    0.41
     gesund
    0.41
     nonprofits
    0.41
    訾
    0.41
    POSITIVE LOGITS
    Mid
    0.43
    tell
    0.41
    op
    0.41
     upp
    0.41
    \[
    0.41
    mid
    0.41
    illy
    0.40
    marker
    0.40
    iena
    0.39
    resume
    0.39
    Act Density 0.000%

    No Known Activations