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

    Neuronpedia

    INDEX
    Explanations

    travel directions, access, or options

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ভোগ্য
    0.43
    假設
    0.43
     catég
    0.42
     discusión
    0.41
    疲れ
    0.41
    ഴു
    0.40
    CompliancePolicy
    0.39
    蠍
    0.39
    挲
    0.39
    貶
    0.39
    POSITIVE LOGITS
     arriving
    0.43
     lowered
    0.43
     arrivals
    0.43
    piry
    0.42
    orph
    0.42
    F
    0.41
     arrives
    0.41
    By
    0.40
    ø
    0.40
    estation
    0.39
    Act Density 0.001%

    No Known Activations