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

    Neuronpedia

    INDEX
    Explanations

    xml code blocks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Story
    0.84
     story
    0.79
     transformed
    0.79
     cook
    0.78
     scented
    0.77
     business
    0.76
     freed
    0.75
     current
    0.74
     arranged
    0.73
     حال
    0.73
    POSITIVE LOGITS
    httphttps
    0.82
    semaphore
    0.79
    varepsilon
    0.77
    rigid
    0.76
     inflexible
    0.76
    Фа
    0.74
    whatever
    0.74
    IRQ
    0.74
    ‌്
    0.73
    ెంబ
    0.73
    Act Density 0.001%

    No Known Activations