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

    Neuronpedia

    INDEX
    Explanations

    __

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    rect
    -0.07
    ecc
    -0.07
     Specify
    -0.07
    texts
    -0.07
     fascism
    -0.07
    _center
    -0.07
    represent
    -0.07
     validar
    -0.07
    draw
    -0.06
    icular
    -0.06
    POSITIVE LOGITS
     здоров
    0.07
    ,…
    0.07
    ='')
    0.07
     диз
    0.07
    uct
    0.07
     Ocean
    0.06
    户外
    0.06
    竞争对手
    0.06
    .intValue
    0.06
     Rogue
    0.06
    Act Density 0.001%

    No Known Activations