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

    Neuronpedia

    INDEX
    Explanations

    states

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    parity
    -0.06
    ocracy
    -0.06
     सद
    -0.06
    Raised
    -0.06
     co
    -0.06
    SEMB
    -0.06
     총
    -0.06
     bothered
    -0.06
     숨
    -0.06
     людини
    -0.06
    POSITIVE LOGITS
     कहत
    0.07
     долж
    0.06
     IsPlainOldData
    0.06
     bulky
    0.06
    ='./
    0.06
    ([\
    0.06
     parsers
    0.06
     libre
    0.06
    .Keys
    0.06
    (jTextField
    0.06
    Act Density 0.002%

    No Known Activations