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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /basic
    -0.06
    ilde
    -0.06
     lateral
    -0.06
    .FLOAT
    -0.06
     đảng
    -0.06
    /C
    -0.06
     earthly
    -0.06
    城市
    -0.06
    роч
    -0.06
    .Lo
    -0.06
    POSITIVE LOGITS
    可以
    0.07
     if
    0.07
     �
    0.07
    .ac
    0.07
     neatly
    0.07
     );↵
    0.06
    ]]↵
    0.06
     '|
    0.06
    breadcrumb
    0.06
    ∏
    0.06
    Act Density 0.004%

    No Known Activations