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

    Neuronpedia

    INDEX
    Explanations

    wearing a charcoal

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ÿ
    0.42
     forman
    0.41
     scoff
    0.41
     lies
    0.41
     ocul
    0.41
     straws
    0.40
     różne
    0.39
     straw
    0.38
     traged
    0.38
     coronary
    0.38
    POSITIVE LOGITS
     közvet
    0.40
     CSO
    0.38
    OSED
    0.36
    剝
    0.36
     YAML
    0.36
    헙
    0.36
     Pathway
    0.35
     ВО
    0.35
    試合
    0.35
     exclusivement
    0.35
    Act Density 0.000%

    No Known Activations