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

    Neuronpedia

    INDEX
    Explanations

    places that host or contain

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    添加到
    0.50
     ocurrido
    0.46
    enters
    0.43
     идут
    0.43
     ocurrir
    0.43
     erfolgt
    0.41
     llegará
    0.41
     Painting
    0.40
     erfolgen
    0.40
    发生在
    0.40
    POSITIVE LOGITS
     hosting
    1.83
     hosts
    1.78
     host
    1.63
    hosting
    1.55
     harbour
    1.53
     Hosting
    1.52
    hosts
    1.51
     harbor
    1.50
     harbors
    1.48
     harboring
    1.48
    Act Density 0.066%

    No Known Activations