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

    Neuronpedia

    INDEX
    Explanations

    research/methods

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Cole
    -0.07
     mListener
    -0.07
    .Children
    -0.07
    _plugin
    -0.07
     değildir
    -0.07
    배
    -0.07
    (datas
    -0.07
    _abs
    -0.06
    oles
    -0.06
     residential
    -0.06
    POSITIVE LOGITS
     antivirus
    0.06
    CLR
    0.06
    oru
    0.06
     identified
    0.06
     ");
↵
    0.06
    еком
    0.06
    (domain
    0.06
    ivirus
    0.06
    ADD
    0.06
    �
    0.05
    Act Density 0.073%

    No Known Activations