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

    Neuronpedia

    INDEX
    Explanations

    rumors and speculation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    忽略
    0.50
     epistem
    0.46
     recommended
    0.44
    推奨
    0.44
    椂
    0.44
     deceptive
    0.44
     toric
    0.44
     totem
    0.42
     "
    0.42
     পায়নি
    0.42
    POSITIVE LOGITS
     rumours
    0.73
     rumour
    0.70
     rumors
    0.66
     rumoured
    0.61
     rumor
    0.60
    噂
    0.59
     rumores
    0.54
     अफवाह
    0.53
    蜚
    0.51
    Rum
    0.49
    Act Density 0.018%

    No Known Activations