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

    Neuronpedia

    INDEX
    Explanations

    majority

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     '../../../
    -0.06
     ech
    -0.06
     uncover
    -0.06
     виход
    -0.06
    744
    -0.06
    _gshared
    -0.06
    気が
    -0.06
    ezpeč
    -0.06
    *******
    -0.06
    ีก
    -0.06
    POSITIVE LOGITS
     majority
    0.13
     Majority
    0.10
     minority
    0.08
    orum
    0.08
    گی
    0.07
    alim
    0.06
    олот
    0.06
     Ř
    0.06
     Apost
    0.06
    62
    0.06
    Act Density 0.004%

    No Known Activations