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

    Neuronpedia

    INDEX
    Explanations

    hair and fur descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Additionally
    0.68
     outra
    0.68
     ebenfalls
    0.63
     redacted
    0.63
     vaguely
    0.63
     matchup
    0.62
     underwhelming
    0.62
     another
    0.61
     kwam
    0.61
    TikTok
    0.61
    POSITIVE LOGITS
     kontinuier
    0.71
     AcOEt
    0.65
     Continuous
    0.64
    ทุก
    0.63
     superbly
    0.63
     optimized
    0.61
     morphogenesis
    0.60
    Continuous
    0.59
    連続
    0.59
     dynamism
    0.59
    Act Density 0.050%

    No Known Activations