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

    Neuronpedia

    INDEX
    Explanations

    positive statements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sus
    -0.06
    σεων
    -0.06
    挂
    -0.06
     Dart
    -0.06
    _emlrt
    -0.06
     bác
    -0.06
     Fresno
    -0.06
     Rising
    -0.06
    xon
    -0.06
    topl
    -0.06
    POSITIVE LOGITS
    =image
    0.06
    oralType
    0.06
    린이
    0.06
     behand
    0.06
    องจาก
    0.06
    termin
    0.06
     유저
    0.06
     šk
    0.06
    리그
    0.06
    ाख
    0.06
    Act Density 0.153%

    No Known Activations