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

    Neuronpedia

    INDEX
    Explanations

    variables or parameters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     blessés
    -0.68
     preuves
    -0.68
     consultato
    -0.66
    AutoresizingMask
    -0.60
    帖最后由
    -0.60
     vectorielle
    -0.60
    .},
    -0.60
     mourir
    -0.59
     filmen
    -0.59
     químicas
    -0.59
    POSITIVE LOGITS
     perfons
    0.55
     heavy
    0.53
    in
    0.51
     different
    0.50
     large
    0.50
    TargetApi
    0.50
     big
    0.49
     individual
    0.49
     number
    0.49
    p
    0.49
    Act Density 0.006%

    No Known Activations