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

    Neuronpedia

    INDEX
    Explanations

    al

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     contributors
    -0.07
    Put
    -0.07
    .merge
    -0.07
     '');↵↵
    -0.07
    (module
    -0.07
     сох
    -0.07
     défini
    -0.07
     poc
    -0.07
    弱
    -0.07
    '',
    -0.07
    POSITIVE LOGITS
    _whitespace
    0.07
     Payload
    0.07
    电商平台
    0.07
    Uber
    0.07
     Wheeler
    0.07
    Ε
    0.06
    BUR
    0.06
    _ble
    0.06
    拥堵
    0.06
    🐘
    0.06
    Act Density 0.230%

    No Known Activations