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

    Neuronpedia

    INDEX
    Explanations

    punctuation and "and"

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     incent
    -0.07
     Lawyers
    -0.06
    .packet
    -0.06
    qml
    -0.06
     Compiler
    -0.06
     Springs
    -0.06
     Vote
    -0.06
     wealthy
    -0.06
    (phone
    -0.06
    -phone
    -0.06
    POSITIVE LOGITS
    ались
    0.07
     impro
    0.07
    (QIcon
    0.07
    etry
    0.06
    rays
    0.06
    Produto
    0.06
    zení
    0.06
    _CONNECTION
    0.06
    /repos
    0.06
     consequently
    0.06
    Act Density 0.124%

    No Known Activations