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

    Neuronpedia

    INDEX
    Explanations

    help injured, observe, every flower, feels cool

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    hard
    0.42
     తమ
    0.39
    now
    0.39
    active
    0.38
    Province
    0.38
    pendiente
    0.38
    美
    0.37
    Active
    0.37
     Peninsula
    0.37
    可
    0.37
    POSITIVE LOGITS
    빕
    0.42
    옻
    0.40
    ђ
    0.40
    !`
    0.40
     bloated
    0.40
    yatiti
    0.39
     ghee
    0.39
     fryer
    0.38
     macer
    0.38
     rotten
    0.38
    Act Density 0.000%

    No Known Activations