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

    Neuronpedia

    INDEX
    Explanations

    publish-subscribe

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Problem
    0.46
    ff
    0.46
    Problem
    0.46
    jší
    0.45
    j
    0.44
    UT
    0.43
    jq
    0.43
     Dominik
    0.41
    legisl
    0.41
    objects
    0.41
    POSITIVE LOGITS
     publier
    0.93
     publish
    0.88
     publicar
    0.84
     publication
    0.81
     публику
    0.80
     publishing
    0.79
     Publish
    0.77
     publishes
    0.77
     publicaciones
    0.74
     publicación
    0.73
    Act Density 0.004%

    No Known Activations