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

    Neuronpedia

    INDEX
    Explanations

    News

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cleaning
    -0.07
     transporter
    -0.06
    BeginInit
    -0.06
     चक
    -0.06
    Industrial
    -0.06
     Efficiency
    -0.06
    annual
    -0.06
     ln
    -0.06
    -0.06
    Constants
    -0.06
    POSITIVE LOGITS
    Philadelphia
    0.06
     الله
    0.06
    .rev
    0.06
    SKTOP
    0.06
     обязательно
    0.06
     머
    0.06
    uitka
    0.06
    현
    0.06
    RACT
    0.06
     yapı
    0.06
    Act Density 0.005%

    No Known Activations