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

    Neuronpedia

    INDEX
    Explanations

    .title

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ropical
    -0.07
    诧
    -0.07
     pulling
    -0.07
    iculos
    -0.07
    谲
    -0.06
     Corm
    -0.06
     erotica
    -0.06
     detr
    -0.06
    ariance
    -0.06
     Sheridan
    -0.06
    POSITIVE LOGITS
    .between
    0.07
    ôi
    0.07
     Clients
    0.07
    乒乓球
    0.07
    ода
    0.06
    mid
    0.06
    _fre
    0.06
    .hd
    0.06
    怎么可能
    0.06
    很容易
    0.06
    Act Density 0.001%

    No Known Activations