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

    Neuronpedia

    INDEX
    Explanations

    Sentence fragments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ánchez
    -0.07
     surviving
    -0.06
     washing
    -0.06
     Văn
    -0.06
    larını
    -0.06
     criticism
    -0.06
     ücret
    -0.06
    ักด
    -0.06
     cleanly
    -0.06
     obed
    -0.06
    POSITIVE LOGITS
    .Standard
    0.07
    (parts
    0.06
     mich
    0.06
    +(
    0.06
    +b
    0.06
    <X
    0.06
     aden
    0.06
    474
    0.06
    Apple
    0.06
    ::|
    0.06
    Act Density 0.000%

    No Known Activations