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

    Neuronpedia

    INDEX
    Explanations

    approved

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Mess
    -0.06
     Luo
    -0.06
    ioxide
    -0.06
    壊
    -0.06
    -source
    -0.06
     Sioux
    -0.06
    ulatory
    -0.06
    人员
    -0.06
    ุส
    -0.06
    cent
    -0.06
    POSITIVE LOGITS
     enlightenment
    0.07
     Originally
    0.07
    succ
    0.06
     supplement
    0.06
     advertisement
    0.06
     respuesta
    0.06
     EntryPoint
    0.06
    .Select
    0.06
    _purchase
    0.06
    FieldValue
    0.06
    Act Density 0.040%

    No Known Activations