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
    鲜血
    -0.08
    emplate
    -0.08
    卫健委
    -0.07
     aims
    -0.07
    قضايا
    -0.07
    .setTexture
    -0.07
    かもし
    -0.07
    avra
    -0.07
     deutschland
    -0.07
    uman
    -0.07
    POSITIVE LOGITS
     {
↵
↵
    0.08
     """
↵
    0.07
    {
↵
↵
    0.07
     /*
    0.07
    (/*
    0.07
     Usage
    0.07
    🎠
    0.07
     (↵↵
    0.07
     );
↵
    0.07
    $v
    0.07
    Act Density 0.013%

    No Known Activations