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

    Neuronpedia

    INDEX
    Explanations

    hyphens

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _ro
    -0.06
     Ci
    -0.06
     Leeds
    -0.06
    �
    -0.06
    �
    -0.06
     cams
    -0.06
     toastr
    -0.06
     Harlem
    -0.05
    rá
    -0.05
    toDouble
    -0.05
    POSITIVE LOGITS
    ниц
    0.07
     referee
    0.07
     सव
    0.06
    -original
    0.06
    MDB
    0.06
     typeName
    0.06
     Blog
    0.06
    /blog
    0.06
    lland
    0.06
    ###↵
    0.06
    Act Density 0.003%

    No Known Activations