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
     Phillies
    -0.07
     Tanzania
    -0.06
     usernames
    -0.06
    _Float
    -0.06
    bservice
    -0.06
     thorough
    -0.06
    <State
    -0.06
    .Blocks
    -0.06
    γκο
    -0.06
    -G
    -0.06
    POSITIVE LOGITS
     install
    0.08
     silky
    0.07
     locales
    0.07
     Stamford
    0.06
    .toJSONString
    0.06
     gi�
    0.06
     empire
    0.06
     tendr
    0.06
    ');↵↵↵
    0.06
     Spy
    0.06
    Act Density 0.145%

    No Known Activations