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

    Neuronpedia

    INDEX
    Explanations

    code swapping elements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    別
    -0.06
    Larry
    -0.06
     �
    -0.06
     Larry
    -0.06
     mime
    -0.06
    lst
    -0.06
    rear
    -0.06
    نع
    -0.06
    ariat
    -0.06
    فهوم
    -0.06
    POSITIVE LOGITS
     acidic
    0.07
    liž
    0.06
     nurse
    0.06
    acoes
    0.06
    _rm
    0.06
     oppon
    0.06
     mosaic
    0.06
    igure
    0.06
    �
    0.06
    -heart
    0.06
    Act Density 0.015%

    No Known Activations