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

    Neuronpedia

    INDEX
    Explanations

    air

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     air
    -0.79
     Air
    -0.73
    Air
    -0.65
    air
    -0.58
     AIR
    -0.56
    AIR
    -0.54
     
    -0.54
     aire
    -0.52
    ’
    -0.50
     $
    -0.47
    POSITIVE LOGITS
     Efq
    1.00
    ſelves
    1.00
    évaluateur
    0.95
    ſelf
    0.94
     itſelf
    0.93
     pleaſure
    0.93
    ьаж
    0.93
     pinulongan
    0.93
     Roskov
    0.90
     متعلقه
    0.89
    Act Density 0.020%

    No Known Activations