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

    Neuronpedia

    INDEX
    Explanations

    + and -

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     VER
    -0.07
     *)"
    -0.07
    lings
    -0.06
    GetY
    -0.06
    `\
    -0.06
        
    -0.06
    oproject
    -0.06
    олот
    -0.06
     refuse
    -0.06
     Notifications
    -0.06
    POSITIVE LOGITS
     questionable
    0.07
     تا
    0.07
     classy
    0.06
     BITS
    0.06
     profoundly
    0.06
     HOR
    0.06
    .driver
    0.06
    .isPresent
    0.06
     Lutheran
    0.06
    .Handler
    0.06
    Act Density 0.049%

    No Known Activations