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

    Neuronpedia

    INDEX
    Explanations

    quotation mark

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    arser
    -0.07
    确认
    -0.06
    abyrinth
    -0.06
     Initi
    -0.06
     sorting
    -0.06
    477
    -0.06
     dogs
    -0.06
    рі
    -0.06
    upro
    -0.06
    toHaveBeenCalledTimes
    -0.06
    POSITIVE LOGITS
    .showMessageDialog
    0.08
     lashes
    0.07
    sage
    0.07
     sunscreen
    0.06
     асп
    0.06
    @Slf
    0.06
    .makeText
    0.06
    vable
    0.06
     джер
    0.06
     mish
    0.06
    Act Density 0.001%

    No Known Activations