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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    :'+
    -0.06
     множе
    -0.06
     Avrupa
    -0.06
     southeast
    -0.06
     dict
    -0.06
     indoors
    -0.06
     VStack
    -0.06
    _BS
    -0.06
    toc
    -0.05
     midfield
    -0.05
    POSITIVE LOGITS
    Policy
    0.07
    chrift
    0.07
    .Scan
    0.07
    MT
    0.07
    termination
    0.06
    OperationException
    0.06
     Sign
    0.06
     م
    0.06
    CRT
    0.06
    adows
    0.06
    Act Density 0.000%

    No Known Activations