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

    Neuronpedia

    INDEX
    Explanations

    vitamins A, D, E, K

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    et
    2.67
    RX
    2.27
    Celsius
    2.23
    s
    2.14
    ka
    2.11
    RNN
    1.94
    ام
    1.93
    THING
    1.90
    CX
    1.89
    ción
    1.88
    POSITIVE LOGITS
    ри
    1.95
     shears
    1.75
    ında
    1.62
    jenigen
    1.62
    を有
    1.59
     incontinence
    1.58
     invari
    1.53
     workmanship
    1.50
     correspondents
    1.48
    न
    1.46
    Act Density 0.200%

    No Known Activations