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

    Neuronpedia

    INDEX
    Explanations

    punctuation/code delimiters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     occas
    -0.06
     Ramadan
    -0.06
     Retreat
    -0.06
     floods
    -0.06
    /me
    -0.06
     Municip
    -0.06
     Cutter
    -0.06
    head
    -0.06
    <S
    -0.06
     Undert
    -0.06
    POSITIVE LOGITS
     gcc
    0.07
     sợ
    0.07
     tern
    0.07
     působ
    0.07
     archival
    0.07
    waitFor
    0.07
    십시오
    0.07
    .handleChange
    0.07
     dejting
    0.06
     تشکیل
    0.06
    Act Density 0.011%

    No Known Activations