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

    Neuronpedia

    INDEX
    Explanations

    AD and BCE dates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     તમારી
    0.58
     votre
    0.54
     importância
    0.53
     cáo
    0.51
     your
    0.50
     Guildford
    0.50
     Conor
    0.50
     cht
    0.50
     Agu
    0.49
     Elovl
    0.49
    POSITIVE LOGITS
    pt
    0.44
    φ
    0.42
    Kes
    0.42
    sinya
    0.41
    西
    0.41
    Пе
    0.40
    skin
    0.40
    UnityEngine
    0.39
    sports
    0.38
    izations
    0.38
    Act Density 0.007%

    No Known Activations