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

    Neuronpedia

    INDEX
    Explanations

    run as administrator

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kunne
    0.40
     определя
    0.38
     könnte
    0.38
    inali
    0.38
    ってみ
    0.37
    Pictures
    0.37
     Determine
    0.37
    चाकी
    0.36
    querySelector
    0.36
     menentukan
    0.36
    POSITIVE LOGITS
    멤버
    0.42
    남도
    0.41
     positivos
    0.39
     vocalist
    0.38
     করুক
    0.38
    Bbb
    0.37
    ADMIN
    0.37
    পোর্ট
    0.37
    炮
    0.37
    GRESS
    0.36
    Act Density 0.000%

    No Known Activations