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

    Neuronpedia

    INDEX
    Explanations

    attention followed by period

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Wit
    0.40
    ميم
    0.39
    loon
    0.38
    atibus
    0.38
    
    0.38
     Doll
    0.37
    Doll
    0.37
    Obl
    0.37
    tım
    0.37
    shima
    0.37
    POSITIVE LOGITS
     psychic
    0.43
     cryptographic
    0.40
     nutritional
    0.38
     defensive
    0.38
     batter
    0.37
     Batter
    0.37
     dredging
    0.36
     regenerative
    0.36
     detoxification
    0.36
     crispy
    0.35
    Act Density 0.003%

    No Known Activations