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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    PerformLayout
    -0.75
    SourceChecksum
    -0.66
    Hentet
    -0.60
     ModelExpression
    -0.58
    ImageContext
    -0.57
     Italijanski
    -0.57
    DeleteBehavior
    -0.56
    FunctionFlags
    -0.55
    #+#
    -0.54
    []>(
    -0.53
    POSITIVE LOGITS
     about
    1.00
     at
    0.95
     as
    0.92
     approximately
    0.71
    about
    0.70
     around
    0.68
     throughout
    0.64
    About
    0.63
     only
    0.62
     just
    0.62
    Act Density 0.010%

    No Known Activations