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

    Neuronpedia

    INDEX
    Explanations

    practical explanation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     finance
    0.46
    োপ
    0.44
     Vander
    0.43
     depois
    0.43
     administra
    0.42
     nain
    0.42
     pais
    0.42
     administrative
    0.42
     Tavares
    0.41
    рий
    0.41
    POSITIVE LOGITS
    cheduled
    0.43
    を果た
    0.42
    etzungen
    0.42
     تربیت
    0.40
     영상을
    0.38
    📽
    0.38
    旃
    0.38
    anz
    0.37
    TGFuZ
    0.37
    zei
    0.37
    Act Density 19.811%

    No Known Activations