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

    Neuronpedia

    INDEX
    Explanations

    purposes only

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    䫝
    0.69
     nutr
    0.65
     nac
    0.63
    ,(((
    0.62
     lauf
    0.62
    \%,
    0.61
    JlcG
    0.61
    ₂,
    0.61
     dissoci
    0.61
     Zach
    0.60
    POSITIVE LOGITS
    only
    0.86
    Only
    0.80
     only
    0.79
     Only
    0.74
    ONLY
    0.69
    만
    0.68
     apenas
    0.65
     tylko
    0.64
    只有
    0.61
     ONLY
    0.59
    Act Density 0.015%

    No Known Activations