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

    Neuronpedia

    INDEX
    Explanations

    pop-up UI

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    demir
    0.32
    𝟭
    0.31
     комби
    0.30
    nagy
    0.30
    痳
    0.30
     angust
    0.30
     регули
    0.30
     கட்டமை
    0.30
    佛教
    0.30
    zocht
    0.29
    POSITIVE LOGITS
    ↵
    0.44
    c
    0.33
    T
    0.32
    L
    0.32
     cell
    0.32
    X
    0.31
    S
    0.31
    R
    0.31
    id
    0.31
    p
    0.30
    Act Density 0.453%

    No Known Activations