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

    Neuronpedia

    INDEX
    Explanations

    code and data formats

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Rad
    -0.07
     cathedral
    -0.07
     Uber
    -0.07
    aller
    -0.06
     Bring
    -0.06
    .invalidate
    -0.06
     IRA
    -0.06
     Nope
    -0.06
    -session
    -0.06
     Sunderland
    -0.06
    POSITIVE LOGITS
    像是
    0.07
    pirit
    0.06
    ýval
    0.06
    魚
    0.06
     ।”↵↵
    0.06
    "]){↵
    0.06
    وص
    0.06
     आपक
    0.06
     giờ
    0.06
                
    0.06
    Act Density 0.032%

    No Known Activations