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

    Neuronpedia

    INDEX
    Explanations

    got it, got this

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Multis
    0.41
    </em>
    0.40
     outlines
    0.40
     Population
    0.39
    olites
    0.38
     Codex
    0.38
    สาน
    0.38
     टु
    0.37
     Outline
    0.37
    悅
    0.37
    POSITIVE LOGITS
     gotta
    0.58
    Got
    0.49
    terdam
    0.47
     rid
    0.46
    henburg
    0.46
    cha
    0.45
    軽
    0.44
     Got
    0.43
    Caught
    0.42
     Gotta
    0.42
    Act Density 0.004%

    No Known Activations