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

    Neuronpedia

    INDEX
    Explanations

    body aches

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     undercover
    0.63
    Cache
    0.60
     SCAN
    0.60
     Cache
    0.59
     scum
    0.59
    逼
    0.59
    ธาน
    0.57
     fake
    0.55
    Flux
    0.54
     vandalism
    0.54
    POSITIVE LOGITS
    cito
    0.62
    ᐃ
    0.57
    往下
    0.56
    Listing
    0.54
     헤
    0.54
    헤
    0.54
    itas
    0.54
     코
    0.54
    adel
    0.53
    ises
    0.53
    Act Density 0.001%

    No Known Activations