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

    Neuronpedia

    INDEX
    Explanations

    applications and projects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    まるで
    0.48
    UE
    0.46
    ও
    0.43
    या
    0.43
    u
    0.42
     yourselves
    0.42
    व्यों
    0.42
    rawler
    0.41
    यां
    0.41
     мебели
    0.41
    POSITIVE LOGITS
     ഇത്
    0.52
     அமிலம்
    0.50
     Anwendung
    0.50
     Ressources
    0.48
     இதே
    0.48
     പ്രവർത്തന
    0.46
    orithms
    0.46
     Jeśli
    0.46
     Allows
    0.45
     Wird
    0.45
    Act Density 0.007%

    No Known Activations