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

    Neuronpedia

    INDEX
    Explanations

    a the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     modèle
    -0.06
     rotated
    -0.06
     additive
    -0.06
     engineers
    -0.06
    designation
    -0.06
    Black
    -0.06
     Skills
    -0.06
    rary
    -0.06
    Threshold
    -0.06
     Watches
    -0.06
    POSITIVE LOGITS
     colorWithRed
    0.07
     apologize
    0.07
    '],['
    0.07
     ca
    0.07
    ctime
    0.07
    üsseldorf
    0.07
     topl
    0.07
    .pnl
    0.06
    masının
    0.06
     pours
    0.06
    Act Density 0.044%

    No Known Activations