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

    Neuronpedia

    INDEX
    Explanations

    ascending chain condition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     débat
    0.43
    他們的
    0.42
    .]+
    0.41
     聞い
    0.41
    พวก
    0.40
    postcss
    0.40
     lustre
    0.40
     canister
    0.40
    ැනි
    0.40
     discursive
    0.39
    POSITIVE LOGITS
     Algeria
    0.41
    मेह
    0.40
     Nei
    0.39
     North
    0.39
    sa
    0.39
     closed
    0.38
    ahara
    0.38
    ⃘
    0.38
     Brother
    0.38
     Earthquake
    0.38
    Act Density 0.108%

    No Known Activations