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

    Neuronpedia

    INDEX
    Explanations

    mask

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Prep
    -0.09
     Friedrich
    -0.08
     Springer
    -0.08
     Everett
    -0.08
     돌
    -0.07
     Schwe
    -0.07
     Cleveland
    -0.07
     Royal
    -0.07
     Fourth
    -0.07
     Elliott
    -0.07
    POSITIVE LOGITS
     Mask
    0.12
    Mask
    0.10
     mask
    0.10
     MASK
    0.10
     masking
    0.09
    mask
    0.09
    MASK
    0.09
    ask
    0.08
     мик
    0.08
     мас
    0.08
    Act Density 0.008%

    No Known Activations