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

    Neuronpedia

    INDEX
    Explanations

    high value items

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    iya
    -0.07
    erman
    -0.06
     Ned
    -0.06
    <Array
    -0.06
    ün
    -0.06
    -wise
    -0.06
    ospels
    -0.06
    ého
    -0.06
     된
    -0.06
     eiusmod
    -0.06
    POSITIVE LOGITS
    identifier
    0.06
     br
    0.06
    .Publish
    0.06
     scaff
    0.06
     brasile
    0.06
    rawtypes
    0.06
    业务
    0.06
    Fill
    0.06
     allies
    0.06
     segreg
    0.06
    Act Density 0.189%

    No Known Activations