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

    Neuronpedia

    INDEX
    Explanations

    Language codes and data entries

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ample
    -0.07
    inkel
    -0.07
    硌
    -0.07
    usa
    -0.07
    陇
    -0.07
    拃
    -0.06
    iks
    -0.06
    lace
    -0.06
     combines
    -0.06
    IMUM
    -0.06
    POSITIVE LOGITS
    ).↵
    0.07
    \":{\"
    0.07
     הש
    0.07
    _upd
    0.07
    อาก
    0.07
     dictates
    0.07
     Murdoch
    0.07
    ופ
    0.07
     sản
    0.07
     WH
    0.07
    Act Density 0.003%

    No Known Activations