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

    Neuronpedia

    INDEX
    Explanations

    questions and answers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     qualifications
    -0.07
    Acceleration
    -0.07
    _accept
    -0.06
     aggregator
    -0.06
     appel
    -0.06
    invitation
    -0.06
     DMA
    -0.06
     onCreateOptionsMenu
    -0.06
     meer
    -0.06
    oce
    -0.06
    POSITIVE LOGITS
    .This
    0.06
    Labour
    0.06
    (()
    0.06
    alore
    0.06
    užel
    0.06
    auto
    0.06
    amins
    0.06
     Möglich
    0.06
    ..........
    0.06
     unleashed
    0.06
    Act Density 0.001%

    No Known Activations