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

    Neuronpedia

    INDEX
    Explanations

    software exploits

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Cp
    -0.07
    fixtures
    -0.07
    яви
    -0.06
     �
    -0.06
    /crypto
    -0.06
     Nylon
    -0.06
     증
    -0.06
     existe
    -0.06
    asyonu
    -0.06
    Pieces
    -0.06
    POSITIVE LOGITS
     attempting
    0.07
     tasty
    0.06
     Làm
    0.06
     establishing
    0.06
    ices
    0.06
     إذا
    0.06
     involuntary
    0.06
     removing
    0.06
     мяс
    0.06
    ✔
    0.06
    Act Density 0.000%

    No Known Activations