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

    Neuronpedia

    INDEX
    Explanations

    psychological, chemical, climbing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     የበ
    0.42
     regrowth
    0.41
     kneeling
    0.40
     Lakes
    0.40
    locationX
    0.40
    xmax
    0.39
     upland
    0.39
    歐洲
    0.38
     हू
    0.38
    𝒙
    0.38
    POSITIVE LOGITS
    明的
    0.44
    $:
    0.41
    ωσ
    0.41
    Issues
    0.40
     TOT
    0.40
    ですね
    0.39
    elems
    0.39
    ៈ
    0.38
    Enumer
    0.38
    ፅ
    0.38
    Act Density 0.000%

    No Known Activations