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

    Neuronpedia

    INDEX
    Explanations

    Code/Technical documentation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <Type
    -0.07
    χό
    -0.07
     curious
    -0.07
     SIDE
    -0.07
    нюю
    -0.06
     Hay
    -0.06
     Written
    -0.06
    .Rect
    -0.06
    ارة
    -0.06
     strips
    -0.06
    POSITIVE LOGITS
    患者
    0.07
     expiration
    0.07
    尿
    0.07
    sein
    0.07
    uch
    0.07
    expiration
    0.06
    Credentials
    0.06
    WithEmail
    0.06
     Newly
    0.06
     Installed
    0.06
    Act Density 0.000%

    No Known Activations