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

    Neuronpedia

    INDEX
    Explanations

    affects obligations and choices

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     confounded
    0.47
    ilibrium
    0.42
    iliar
    0.41
    кансер
    0.41
    ில்லியன்
    0.40
     ambition
    0.40
     ingested
    0.40
    𝙮
    0.40
    滪
    0.39
     transplanted
    0.39
    POSITIVE LOGITS
     seulement
    0.52
     série
    0.49
     vidéo
    0.48
     Türkçe
    0.48
     moteur
    0.48
     bhuv
    0.48
     suivant
    0.48
     pédagog
    0.48
     télécharg
    0.48
     tjen
    0.48
    Act Density 0.005%

    No Known Activations