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

    Neuronpedia

    INDEX
    Explanations

    comparisons

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .fx
    -0.07
    τερο
    -0.07
    .cart
    -0.06
    byss
    -0.06
    मत
    -0.06
    řejmě
    -0.06
    .Messages
    -0.06
     Angebot
    -0.06
    /INFO
    -0.06
    、「
    -0.06
    POSITIVE LOGITS
    aising
    0.07
    usage
    0.07
     Barrett
    0.06
     gi�
    0.06
    주시
    0.06
    /chart
    0.06
    illy
    0.06
    _CSR
    0.06
     holland
    0.06
     reflecting
    0.06
    Act Density 0.011%

    No Known Activations