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

    Neuronpedia

    INDEX
    Explanations

    real-world consequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Checked
    0.85
     Rendering
    0.84
    ை
    0.84
     Check
    0.81
     görüntü
    0.79
     Turned
    0.79
     Assessment
    0.79
     Checking
    0.78
    Expo
    0.78
     <$>
    0.77
    POSITIVE LOGITS
    estones
    1.13
    life
    1.03
    gie
    0.98
    有的
    0.97
    слов
    0.97
    tained
    0.97
    restrial
    0.96
     temporadas
    0.96
    isieren
    0.96
    time
    0.96
    Act Density 0.019%

    No Known Activations