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

    Neuronpedia

    INDEX
    Explanations

    sequence order progression time setting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ежеднев
    0.38
    Hoe
    0.37
    Rec
    0.37
     CW
    0.37
    COD
    0.36
    Forge
    0.36
     fong
    0.36
     walking
    0.35
    FW
    0.35
     Hoe
    0.35
    POSITIVE LOGITS
    katore
    0.46
    巒
    0.39
    ငံ
    0.39
     Zeitpunkt
    0.39
     illetve
    0.37
    ranno
    0.37
    رات
    0.36
     multivalued
    0.36
     တယ်
    0.36
     mutter
    0.36
    Act Density 0.000%

    No Known Activations