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

    Neuronpedia

    INDEX
    Explanations

    about or on topics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     iteratively
    0.48
     triage
    0.47
     parsing
    0.46
     autore
    0.46
     seznam
    0.45
     parse
    0.45
     strips
    0.45
     bytecode
    0.45
     checklists
    0.44
     chante
    0.44
    POSITIVE LOGITS
     tentang
    0.59
     tema
    0.55
    关于
    0.52
    เกี่ยวกับ
    0.51
     тему
    0.50
     عن
    0.49
     about
    0.48
     về
    0.47
     посвящен
    0.47
     върху
    0.46
    Act Density 0.119%

    No Known Activations