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

    Neuronpedia

    INDEX
    Explanations

    Lists

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    sunuz
    -0.06
     Opr
    -0.06
    =plt
    -0.06
     girişim
    -0.06
    ;
↵
↵
↵
↵
    -0.06
    /Typography
    -0.06
    まる
    -0.06
    층의
    -0.06
    吾
    -0.06
    _simps
    -0.06
    POSITIVE LOGITS
     [&](
    0.07
    cause
    0.07
     flavours
    0.06
    _todo
    0.06
    latent
    0.06
    用户
    0.06
    izard
    0.06
    _And
    0.06
    xba
    0.06
    Browser
    0.06
    Act Density 0.076%

    No Known Activations