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

    Neuronpedia

    INDEX
    Explanations

    8

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    草原
    -0.08
    [vi
    -0.08
     sonic
    -0.08
     cavity
    -0.07
     paramInt
    -0.07
     Planet
    -0.07
    Inlining
    -0.07
     pv
    -0.07
     כולל
    -0.07
    .Service
    -0.07
    POSITIVE LOGITS
    process
    0.07
     Processing
    0.07
     bet
    0.07
     Low
    0.07
     �
    0.06
     frame
    0.06
    CEPTION
    0.06
    )};↵
    0.06
     POR
    0.06
     Easy
    0.06
    Act Density 0.001%

    No Known Activations