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

    Neuronpedia

    INDEX
    Explanations

    there are

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    שורים
    0.48
     থাকেন
    0.45
     ఉన్నాయి
    0.44
    iciones
    0.44
     jsou
    0.43
     ideias
    0.43
    ంచరీలు
    0.43
     አሉ
    0.43
     هناك
    0.42
    isterschaften
    0.42
    POSITIVE LOGITS
     tamen
    0.45
     indeed
    0.44
     многих
    0.44
    ହି
    0.43
    یثیت
    0.43
    indeed
    0.42
     många
    0.42
     pembuatan
    0.40
     flera
    0.40
     speedboat
    0.39
    Act Density 0.010%

    No Known Activations