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

    Neuronpedia

    INDEX
    Explanations

    IQ, Kanji, Egyptian, god

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    velte
    0.47
    OVE
    0.46
     ஆய
    0.46
     brind
    0.45
     moveable
    0.44
     mà
    0.43
    ifically
    0.42
    recated
    0.42
    侍
    0.42
     cho
    0.41
    POSITIVE LOGITS
    id
    0.48
    charging
    0.46
    estion
    0.45
    стта
    0.44
     recharging
    0.43
     технологі
    0.43
    grams
    0.42
     charging
    0.42
    foundation
    0.42
     Broncos
    0.42
    Act Density 0.000%

    No Known Activations