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

    Neuronpedia

    INDEX
    Explanations

    sounds

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Depend
    -0.07
     conseg
    -0.07
     ilaç
    -0.07
    ragon
    -0.06
     lời
    -0.06
    ̃
    -0.06
    ，《
    -0.06
     в
    -0.06
     у
    -0.06
    (parcel
    -0.06
    POSITIVE LOGITS
    争
    0.07
    -provider
    0.06
     khuẩn
    0.06
    rypton
    0.06
     recognizing
    0.06
    _trigger
    0.06
    adiens
    0.06
    Bi
    0.06
    0.06
     returnType
    0.06
    Act Density 1.231%

    No Known Activations