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

    Neuronpedia

    INDEX
    Explanations

    distinctive features

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Analytics
    -0.07
     analytics
    -0.07
     snow
    -0.07
    ILLISECONDS
    -0.06
    (pkt
    -0.06
    Credentials
    -0.06
    /******************************************************************************/↵
    -0.06
    ku
    -0.06
    specifier
    -0.06
    Perform
    -0.06
    POSITIVE LOGITS
    ��
    0.07
    phase
    0.07
    Cars
    0.07
    tanggal
    0.06
     kp
    0.06
    elerinde
    0.06
    ooth
    0.06
     quảng
    0.06
    itus
    0.06
     رضا
    0.06
    Act Density 0.068%

    No Known Activations