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

    Neuronpedia

    INDEX
    Explanations

    physics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.08
    rette
    -0.08
    ZW
    -0.07
    .Display
    -0.07
    🙈
    -0.07
    🙀
    -0.07
    璀璨
    -0.07
    Feel
    -0.07
     Psr
    -0.07
     zn
    -0.07
    POSITIVE LOGITS
     원
    0.07
    堎
    0.07
    ้อม
    0.07
    髻
    0.07
    工作
    0.07
     `"
    0.07
    还是比较
    0.07
    息
    0.07
    ('"
    0.07
    ้อง
    0.07
    Act Density 0.006%

    No Known Activations