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

    Neuronpedia

    INDEX
    Explanations

    questions asking for lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    摶
    0.41
     pracuje
    0.40
     মুজিবকে
    0.40
     చిత్రం
    0.39
    وون
    0.38
    following
    0.38
    AFTER
    0.38
    정이
    0.38
     Почему
    0.38
     Anfrage
    0.37
    POSITIVE LOGITS
     benefits
    0.83
     advantages
    0.77
     Benefits
    0.75
     symptoms
    0.74
     beneficios
    0.73
     benefícios
    0.73
     pitfalls
    0.73
     disadvantages
    0.72
    advantages
    0.67
     Advantages
    0.66
    Act Density 0.001%

    No Known Activations