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

    Neuronpedia

    INDEX
    Explanations

    hot numbers and offers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    伦
    0.40
     умова
    0.39
     মুজিবর
    0.38
     FUNC
    0.38
     buil
    0.38
    وق
    0.37
     Prerequisites
    0.37
    DebuggerNonUser
    0.37
     atoi
    0.37
     ench
    0.36
    POSITIVE LOGITS
    フルーツ
    0.45
    ົ້າ
    0.44
    astien
    0.42
    }->
    0.42
    chosen
    0.41
    áč
    0.41
    製の
    0.41
    green
    0.40
    vien
    0.40
    Eff
    0.40
    Act Density 0.012%

    No Known Activations