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

    Neuronpedia

    INDEX
    Explanations

    Science, technology, politics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    exo
    -0.07
    Ja
    -0.07
    iane
    -0.06
     FIR
    -0.06
    ycastle
    -0.06
    ноп
    -0.06
    대의
    -0.06
    едь
    -0.06
    itori
    -0.06
     orientation
    -0.06
    POSITIVE LOGITS
    .note
    0.06
    /save
    0.06
    을
    0.06
    _started
    0.06
    .chrome
    0.06
     Moines
    0.06
     unparalleled
    0.06
    =>{↵
    0.06
    .CompilerServices
    0.06
     [↵
    0.06
    Act Density 0.190%

    No Known Activations