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

    Neuronpedia

    INDEX
    Explanations

    ais

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ais
    -1.17
     picked
    -0.73
     picking
    -0.69
     Mack
    -0.60
     Picking
    -0.59
    AIS
    -0.56
    urra
    -0.49
     pickup
    -0.49
     Pickup
    -0.49
    λε
    -0.47
    POSITIVE LOGITS
     Efq
    0.70
     Monfieur
    0.68
     sanitaires
    0.66
     aDecoder
    0.66
     الحره
    0.66
     BoxFit
    0.66
    +#+#
    0.66
    UnusedPrivate
    0.65
     חיצוניים
    0.64
     purpoſe
    0.64
    Act Density 0.111%

    No Known Activations