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

    Neuronpedia

    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Invariant
    -0.06
     ';
    -0.06
    console
    -0.06
    willReturn
    -0.06
    лю
    -0.06
    يري
    -0.06
    .baomidou
    -0.06
    ーション
    -0.06
    SAME
    -0.06
    الى
    -0.06
    POSITIVE LOGITS
    NOW
    0.07
     defs
    0.07
    aly
    0.07
    (Api
    0.06
    態
    0.06
    isors
    0.06
    漏
    0.06
    阅
    0.06
     SCR
    0.06
    _CSR
    0.06
    Act Density 0.213%

    No Known Activations