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

    Neuronpedia

    INDEX
    Explanations

    certain parts of speech

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     redirect
    0.54
     interesado
    0.52
     field
    0.52
     cervical
    0.47
     automaker
    0.47
     financial
    0.47
     lobbying
    0.46
     scouting
    0.46
     watershed
    0.46
     controversial
    0.45
    POSITIVE LOGITS
     великолеп
    0.60
    ᓛ
    0.60
     дуже
    0.56
     отлично
    0.55
     очень
    0.53
     Очень
    0.51
     собственно
    0.50
    СТИ
    0.49
     отли
    0.49
     Фран
    0.48
    Act Density 0.002%

    No Known Activations