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

    Neuronpedia

    INDEX
    Explanations

    Spanish and foreign words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ⟋
    0.30
    ൦
    0.29
    ྵ
    0.29
    }$')
    0.28
     advers
    0.28
    ㅔ
    0.27
    싶
    0.27
    扃
    0.27
     syncing
    0.27
    🕹
    0.27
    POSITIVE LOGITS
    ira
    0.33
    aka
    0.29
    ara
    0.29
    ama
    0.29
    colo
    0.28
    aki
    0.27
    aga
    0.27
     کجا
    0.27
    uki
    0.26
    idea
    0.26
    Act Density 0.058%

    No Known Activations