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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    vm
    -0.07
    -elected
    -0.07
    sj
    -0.07
    trfs
    -0.07
    iversal
    -0.07
    ulnerable
    -0.06
    Michelle
    -0.06
    thumbs
    -0.06
    books
    -0.06
     soát
    -0.06
    POSITIVE LOGITS
     h
    0.07
    _land
    0.07
     lor
    0.07
    �
    0.07
    神话
    0.07
     largo
    0.07
     Boyd
    0.07
     bolster
    0.07
    하는
    0.06
     unn
    0.06
    Act Density 0.042%

    No Known Activations