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

    Neuronpedia

    INDEX
    Explanations

    scientific publications

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Scho
    -0.08
    ész
    -0.08
     Sheila
    -0.07
    民间
    -0.07
    ért
    -0.07
     mia
    -0.07
    .newBuilder
    -0.07
    .schema
    -0.07
     suffice
    -0.06
     meshes
    -0.06
    POSITIVE LOGITS
    _<?
    0.07
    (ok
    0.07
    無
    0.07
     Holidays
    0.07
    סאות
    0.07
     большим
    0.06
    🦒
    0.06
     Packaging
    0.06
    𠮷
    0.06
    (format
    0.06
    Act Density 0.000%

    No Known Activations