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

    Neuronpedia

    INDEX
    Explanations

    say "every"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    lients
    -0.08
     kurs
    -0.07
     צריכה
    -0.07
     fighter
    -0.06
    auté
    -0.06
    ysz
    -0.06
    слов
    -0.06
    證
    -0.06
    miner
    -0.06
     kijken
    -0.06
    POSITIVE LOGITS
     ..."↵
    0.07
    _LOADED
    0.07
     חינם
    0.07
    
    0.06
    employment
    0.06
    EditMode
    0.06
    ἦ
    0.06
    🕸
    0.06
    🛑
    0.06
    dem
    0.06
    Act Density 0.260%

    No Known Activations