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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    реб
    -0.07
    :L
    -0.07
    .trip
    -0.07
     dumb
    -0.07
     incididunt
    -0.06
    yu
    -0.06
    hr
    -0.06
    ้แก
    -0.06
     historic
    -0.06
    ModelIndex
    -0.06
    POSITIVE LOGITS
    anium
    0.07
    比較
    0.06
    (),"
    0.06
    .findElement
    0.06
    登
    0.06
     brilliant
    0.06
    .]
    0.06
     zby
    0.06
    SharedPtr
    0.06
    .scrollTo
    0.06
    Act Density 0.031%

    No Known Activations