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

    Neuronpedia

    INDEX
    Explanations

    only

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    اطعة
    -0.07
    polation
    -0.06
     sahiptir
    -0.06
    usage
    -0.06
     zaman
    -0.06
     Workspace
    -0.06
    (att
    -0.06
    �
    -0.06
     mexico
    -0.06
    ¦
    -0.06
    POSITIVE LOGITS
    口
    0.07
    =_('
    0.07
     subgroup
    0.07
    .listen
    0.06
    Extract
    0.06
     mocking
    0.06
    clock
    0.06
    used
    0.06
     ของ
    0.06
     Dell
    0.06
    Act Density 0.002%

    No Known Activations