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

    Neuronpedia

    INDEX
    Explanations

    scientific notation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     некотор
    -0.07
     nettsteder
    -0.07
     unsafe
    -0.06
    Return
    -0.06
     gösteren
    -0.06
    (\$
    -0.06
     rebell
    -0.06
    <tr
    -0.06
     syrup
    -0.06
     nokt
    -0.06
    POSITIVE LOGITS
     서
    0.07
    Gesture
    0.07
     [])↵
    0.06
    istence
    0.06
    {},↵
    0.06
    fm
    0.06
     Port
    0.06
    вищ
    0.06
     dile
    0.06
    .song
    0.06
    Act Density 0.054%

    No Known Activations