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

    Neuronpedia

    INDEX
    Explanations

    to/the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _BEGIN
    -0.09
    <any
    -0.08
     recognizer
    -0.08
    .any
    -0.07
    .writeHead
    -0.07
     كثير
    -0.07
    ={<
    -0.07
    箬
    -0.07
    机关
    -0.07
    -bootstrap
    -0.07
    POSITIVE LOGITS
    yrı
    0.07
     NFL
    0.07
    /drivers
    0.06
    ≴
    0.06
     Transmit
    0.06
    兵力
    0.06
    גוב
    0.06
    iation
    0.06
     lø
    0.06
    吳
    0.06
    Act Density 0.019%

    No Known Activations