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

    Neuronpedia

    INDEX
    Explanations

    .org

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Relations
    -0.07
     rift
    -0.07
    097
    -0.07
     ance
    -0.07
    .direction
    -0.07
    rawn
    -0.06
    alent
    -0.06
    Warn
    -0.06
     Nas
    -0.06
    uplicated
    -0.06
    POSITIVE LOGITS
    .getLine
    0.07
    ОВ
    0.06
    (inv
    0.06
    .evaluate
    0.06
     giai
    0.06
     Saying
    0.06
    -instance
    0.06
    :'+
    0.06
     imageURL
    0.06
     contributes
    0.06
    Act Density 0.001%

    No Known Activations