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

    Neuronpedia

    INDEX
    Explanations

    angle brackets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -Semitic
    -0.07
     homophobic
    -0.06
    ую
    -0.06
     nedeniyle
    -0.06
     lobby
    -0.06
     backdrop
    -0.06
     lawn
    -0.06
     Rolling
    -0.06
    道路
    -0.06
    �
    -0.06
    POSITIVE LOGITS
    WB
    0.06
    費
    0.06
     cub
    0.06
     거래
    0.06
     shaft
    0.06
     passions
    0.06
    거래
    0.06
    าหาร
    0.06
     HEX
    0.06
    _SK
    0.06
    Act Density 0.005%

    No Known Activations