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

    Neuronpedia

    INDEX
    Explanations

    what is the topic

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     dependence
    0.46
     guidelines
    0.46
     regimens
    0.46
     evolution
    0.44
    oglycos
    0.43
     each
    0.43
     to
    0.42
     endowment
    0.42
     topologies
    0.42
     require
    0.42
    POSITIVE LOGITS
     вас
    0.52
     вам
    0.50
     сде
    0.49
     हमारी
    0.48
     abogado
    0.47
     vám
    0.46
    фри
    0.46
     kematian
    0.46
     เล
    0.46
    红包
    0.45
    Act Density 0.006%

    No Known Activations