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

    Neuronpedia

    INDEX
    Explanations

    yourself

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Aluminum
    -0.07
     고객
    -0.07
     dames
    -0.07
     HEAP
    -0.07
     Orlando
    -0.07
     Tro
    -0.07
    َا
    -0.07
    stor
    -0.07
    .Commands
    -0.07
    ורחים
    -0.07
    POSITIVE LOGITS
    +k
    0.07
     binding
    0.07
    怏
    0.07
     sợ
    0.07
    -delay
    0.07
    Dst
    0.07
    Gender
    0.07
     lack
    0.07
     participación
    0.06
    вшис
    0.06
    Act Density 0.104%

    No Known Activations