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

    Neuronpedia

    INDEX
    Explanations

    measurement

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    که
    -0.06
    repository
    -0.06
     accompanying
    -0.06
     which
    -0.06
     Sailor
    -0.06
     Diese
    -0.06
    tax
    -0.06
     Which
    -0.06
     identical
    -0.06
    reject
    -0.06
    POSITIVE LOGITS
    '>↵↵
    0.06
     cert
    0.06
    Unary
    0.06
    ')+
    0.06
    ...)↵
    0.06
     профессиональ
    0.06
    _paths
    0.06
     멀
    0.06
     COOKIE
    0.06
     bohat
    0.06
    Act Density 0.112%

    No Known Activations