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

    Neuronpedia

    INDEX
    Explanations

    code or documentation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.07
    캐
    -0.07
    chos
    -0.07
    Again
    -0.07
    _identity
    -0.07
     éxito
    -0.06
    .ne
    -0.06
     '..',
    -0.06
    590
    -0.06
     왜
    -0.06
    POSITIVE LOGITS
     Implement
    0.07
    ους
    0.06
     uterus
    0.06
     TextArea
    0.06
    lásil
    0.06
    ",&
    0.06
     телеф
    0.06
     JAN
    0.06
     Lounge
    0.06
     Cosmic
    0.06
    Act Density 0.001%

    No Known Activations