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

    Neuronpedia

    INDEX
    Explanations

    Chinese characters that reference upward movement or positioning

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    上, shang, on, above

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     HasFactory
    -0.58
    anasia
    -0.57
    trino
    -0.57
    SharedCtor
    -0.57
     EventEmitter
    -0.57
    continence
    -0.57
    batore
    -0.56
     Miel
    -0.54
    tamol
    -0.53
    riwal
    -0.52
    POSITIVE LOGITS
    上
    0.81
     上
    0.71
    Shang
    0.63
     Shang
    0.61
    子上
    0.60
     cima
    0.60
     Above
    0.58
     Upper
    0.58
     up
    0.57
     Upload
    0.57
    Act Density 0.005%

    No Known Activations