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

    Neuronpedia

    INDEX
    Explanations

    .map or flatMap

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    inals
    -0.07
    运输
    -0.07
    vanced
    -0.07
    .Owner
    -0.07
     hype
    -0.07
     Israelis
    -0.07
    恐怕
    -0.07
    再来
    -0.06
     натуральн
    -0.06
     Fiji
    -0.06
    POSITIVE LOGITS
    >>();↵
    0.07
    .clicked
    0.07
    _documents
    0.07
     illum
    0.07
    .LookAndFeel
    0.07
     chir
    0.07
    _grp
    0.07
     воздух
    0.07
     البع
    0.07
    >();↵
    0.06
    Act Density 0.002%

    No Known Activations