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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     anecd
    -0.07
     persecution
    -0.07
     Lair
    -0.06
    uan
    -0.06
    .DecimalField
    -0.06
    haps
    -0.06
    uania
    -0.06
    قات
    -0.06
    bnb
    -0.05
     찬
    -0.05
    POSITIVE LOGITS
     دانشگاه
    0.07
     ні
    0.06
    ροχή
    0.06
    .toggle
    0.06
    .Stream
    0.06
    stdlib
    0.06
     téměř
    0.06
    connect
    0.06
    (Stream
    0.06
     Т
    0.06
    Act Density 0.000%

    No Known Activations