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

    Neuronpedia

    INDEX
    Explanations

    current action or currency

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    부가
    0.42
     butter
    0.38
     quartile
    0.37
    itian
    0.36
     flushed
    0.36
     atmosphere
    0.35
    vest
    0.35
     Wechsler
    0.35
     Butter
    0.34
     vest
    0.34
    POSITIVE LOGITS
     existencia
    0.42
    ératures
    0.42
     waarmee
    0.41
    зже
    0.39
    SetName
    0.39
     وجود
    0.39
     pourquoi
    0.38
     veux
    0.38
     estés
    0.38
    ੯
    0.38
    Act Density 0.000%

    No Known Activations