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

    Neuronpedia

    INDEX
    Explanations

    unicorn

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     config
    -0.07
    -block
    -0.07
     stimuli
    -0.07
     rulings
    -0.07
     comment
    -0.07
     reaches
    -0.07
     réal
    -0.07
    -0.07
     thermal
    -0.07
    claims
    -0.07
    POSITIVE LOGITS
     Unicorn
    0.09
     unicorn
    0.09
    unicorn
    0.07
    ücü
    0.07
    ㅎ
    0.07
    ินทร
    0.06
     برای
    0.06
    Вы
    0.06
     합니다
    0.06
    €�
    0.06
    Act Density 0.002%

    No Known Activations