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

    Neuronpedia

    INDEX
    Explanations

    interval

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Small
    -0.07
    ('[
    -0.07
    .CREATED
    -0.07
    user
    -0.06
    .place
    -0.06
     codigo
    -0.06
     Plants
    -0.06
     rocking
    -0.06
    .design
    -0.06
     user
    -0.06
    POSITIVE LOGITS
     interval
    0.09
     Interval
    0.08
    #:
    0.08
    ervals
    0.07
    -ext
    0.07
    olem
    0.07
    руб
    0.07
     dial
    0.07
    ahat
    0.07
     ит
    0.07
    Act Density 0.008%

    No Known Activations