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

    Neuronpedia

    INDEX
    Explanations

    so

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    [['
    -0.07
    ダイ
    -0.06
     unrelated
    -0.06
    ###
    -0.06
     ότι
    -0.06
     aden
    -0.06
    _DUMP
    -0.06
    �
    -0.06
    uil
    -0.06
     Abdel
    -0.06
    POSITIVE LOGITS
     so
    0.17
     So
    0.15
     SO
    0.13
    So
    0.12
    .So
    0.12
    so
    0.11
    SO
    0.11
    (so
    0.10
    -so
    0.10
    .so
    0.10
    Act Density 0.099%

    No Known Activations