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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     aws
    -0.07
    辜负
    -0.07
    澳
    -0.07
     Wrapper
    -0.06
    .Shapes
    -0.06
    <stdio
    -0.06
    ♂
    -0.06
    _CODES
    -0.06
     한국
    -0.06
    ☒
    -0.06
    POSITIVE LOGITS
    屯
    0.07
    有所
    0.07
    orem
    0.07
    RES
    0.07
    blem
    0.07
    价值观
    0.07
    coln
    0.07
    幅度
    0.07
    rades
    0.07
    丢失
    0.07
    Act Density 0.014%

    No Known Activations