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

    Neuronpedia

    INDEX
    Explanations

    matrix multiplication

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     MSNBC
    -0.08
     �
    -0.07
    /lang
    -0.07
    catalog
    -0.07
    乐意
    -0.07
    宓
    -0.07
    �
    -0.07
    _buf
    -0.06
     reluct
    -0.06
    -watch
    -0.06
    POSITIVE LOGITS
     dau
    0.07
     project
    0.07
    Eu
    0.07
     cleared
    0.07
     carried
    0.06
    .from
    0.06
     tore
    0.06
    uida
    0.06
     Eu
    0.06
    external
    0.06
    Act Density 0.029%

    No Known Activations