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

    Neuronpedia

    INDEX
    Explanations

    Serif

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    젠
    -0.07
    ét
    -0.07
    iscing
    -0.06
    міністра
    -0.06
    portlet
    -0.06
     Indonesia
    -0.06
    Rua
    -0.06
     furn
    -0.06
    unteers
    -0.06
     �
    -0.06
    POSITIVE LOGITS
     ))↵
    0.07
     외국
    0.07
     Büyük
    0.07
     бок
    0.06
    位
    0.06
    .factory
    0.06
    파일
    0.06
     epith
    0.06
    ('',
    0.06
     Vad
    0.06
    Act Density 0.000%

    No Known Activations