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

    Neuronpedia

    INDEX
    Explanations

    Long form text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    fires
    -0.07
    Flush
    -0.06
     shed
    -0.06
    ibal
    -0.06
     人
    -0.06
    овал
    -0.06
    .generated
    -0.06
     healed
    -0.06
     KeyError
    -0.06
     ｜
    -0.06
    POSITIVE LOGITS
     acknow
    0.07
     gre
    0.06
     Platz
    0.06
     ať
    0.06
     hak
    0.06
     customers
    0.06
    �
    0.06
    pter
    0.06
    Td
    0.06
     рід
    0.06
    Act Density 0.263%

    No Known Activations