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

    Neuronpedia

    INDEX
    Explanations

    financial reports and changes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     membayar
    0.53
    नल
    0.52
     ಚುನ
    0.50
    насти
    0.48
     awaits
    0.48
    讹
    0.47
     chien
    0.47
     $((
    0.47
     पॉप
    0.47
     hicimos
    0.47
    POSITIVE LOGITS
    i
    0.59
    ร
    0.53
    e
    0.47
    ⒉
    0.45
    台中
    0.44
    3
    0.44
     Realt
    0.41
     mer
    0.40
    民眾
    0.40
    ⅔
    0.40
    Act Density 0.000%

    No Known Activations