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

    Neuronpedia

    INDEX
    Explanations

    instruction/rules

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _acl
    -0.07
    Cog
    -0.06
    udeau
    -0.06
    _ACT
    -0.06
    fans
    -0.06
     histo
    -0.06
     Giáo
    -0.06
    quierda
    -0.06
     plaint
    -0.06
    -arm
    -0.06
    POSITIVE LOGITS
     alan
    0.07
    .paginator
    0.06
     ödem
    0.06
     był
    0.06
    ryan
    0.06
     yüksek
    0.06
     dafür
    0.06
     Teil
    0.06
     Descriptor
    0.06
     修改
    0.06
    Act Density 0.009%

    No Known Activations