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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    IQUE
    -0.06
    /books
    -0.06
    -employed
    -0.06
    .look
    -0.06
     아침
    -0.06
    _review
    -0.06
    _EMP
    -0.06
    /";↵↵
    -0.06
    ยน
    -0.06
     joe
    -0.06
    POSITIVE LOGITS
    zione
    0.07
     》
    0.07
    BIT
    0.07
     Nagar
    0.06
     suspicions
    0.06
     squirt
    0.06
     Bere
    0.06
     goodness
    0.06
    ně
    0.06
     getCode
    0.06
    Act Density 0.004%

    No Known Activations