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

    Neuronpedia

    INDEX
    Explanations

    patent numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     PayPal
    -0.07
     Increasing
    -0.07
    (Collectors
    -0.07
    bl
    -0.07
    errmsg
    -0.06
     liar
    -0.06
     Carr
    -0.06
     LINK
    -0.06
    ��
    -0.06
    ψ
    -0.06
    POSITIVE LOGITS
     eliminates
    0.06
    (Arg
    0.06
     ",↵
    0.06
    ]=$
    0.06
     ['$
    0.06
    ephy
    0.06
                             ↵
    0.06
    (digits
    0.06
     """↵
    0.06
    _An
    0.06
    Act Density 0.008%

    No Known Activations