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

    Neuronpedia

    INDEX
    Explanations

    binary numbers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     vitae
    -0.08
     compassion
    -0.07
    ไฟ
    -0.07
     inspiring
    -0.07
    .no
    -0.07
     '%$
    -0.07
    RTC
    -0.07
    🔖
    -0.07
     Craig
    -0.07
     userName
    -0.07
    POSITIVE LOGITS
    ]\
    0.07
    ’é
    0.07
    }\\
    0.07
    ]]
    0.06
     spin
    0.06
    ()})↵
    0.06
    分析
    0.06
    resolution
    0.06
    си
    0.06
     safer
    0.06
    Act Density 0.001%

    No Known Activations