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

    Neuronpedia

    INDEX
    Explanations

    false dilemma

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     HF
    0.41
     jogs
    0.41
     Grilled
    0.39
     grilled
    0.38
     HJ
    0.38
    blocking
    0.38
    क्तिक
    0.38
     મા
    0.38
     প্রকাশ্যে
    0.38
     Lom
    0.37
    POSITIVE LOGITS
     저장
    0.41
     сохранить
    0.40
     speichern
    0.40
    быз
    0.40
     зберіга
    0.39
     نہیں۔
    0.39
    iramente
    0.38
     suficient
    0.38
    Vancouver
    0.37
    Placement
    0.37
    Act Density 0.000%

    No Known Activations