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

    Neuronpedia

    INDEX
    Explanations

    generate

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    uml
    -0.07
    ाइ
    -0.07
    .TextField
    -0.07
    ob
    -0.06
    _equals
    -0.06
    -owner
    -0.06
    рь
    -0.06
     даних
    -0.06
     Licensed
    -0.06
    рес
    -0.06
    POSITIVE LOGITS
     erót
    0.06
     viv
    0.06
    PUT
    0.06
     wooded
    0.06
    need
    0.06
     chew
    0.06
    érica
    0.06
    inal
    0.06
    putc
    0.06
    stractions
    0.05
    Act Density 0.008%

    No Known Activations