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

    Neuronpedia

    INDEX
    Explanations

    *

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    डर
    -0.08
     hete
    -0.07
    방법
    -0.07
     masterpiece
    -0.07
     pozdě
    -0.07
     trai
    -0.07
    家伙
    -0.06
     loosely
    -0.06
     ssid
    -0.06
    нерг
    -0.06
    POSITIVE LOGITS
     strengthening
    0.08
     prick
    0.07
    opcode
    0.07
     UNESCO
    0.06
     intéress
    0.06
     asoci
    0.06
    (assign
    0.06
    číta
    0.06
    上传
    0.06
    int
    0.06
    Act Density 0.068%

    No Known Activations