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

    Neuronpedia

    INDEX
    Explanations

    onym

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -needed
    -0.07
    的一
    -0.07
     expected
    -0.07
     pallet
    -0.06
    的大
    -0.06
     altogether
    -0.06
     tamamen
    -0.06
     lens
    -0.06
    děl
    -0.06
    ад
    -0.06
    POSITIVE LOGITS
     Esk
    0.07
    oystick
    0.07
    ذا
    0.07
    .Autowired
    0.07
     entitled
    0.06
    175
    0.06
    178
    0.06
    $is
    0.06
     sauna
    0.06
     arrows
    0.06
    Act Density 0.003%

    No Known Activations