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

    Neuronpedia

    INDEX
    Explanations

    written

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    planation
    -0.07
    Sortable
    -0.06
     Genetics
    -0.06
     phoneNumber
    -0.06
     cow
    -0.06
    iêu
    -0.06
     heed
    -0.06
     Sé
    -0.06
     Fakült
    -0.06
     рамках
    -0.06
    POSITIVE LOGITS
    �
    0.07
    เลย
    0.07
    पर
    0.06
    classNames
    0.06
    蘭
    0.06
    もしれない
    0.06
     blinking
    0.06
     CIM
    0.06
     Kes
    0.06
     集
    0.06
    Act Density 0.001%

    No Known Activations