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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     actionBar
    -0.08
     utils
    -0.07
     elusive
    -0.07
    ZH
    -0.07
    나라
    -0.07
     whipping
    -0.06
    png
    -0.06
     ICollection
    -0.06
    .endswith
    -0.06
    atalog
    -0.06
    POSITIVE LOGITS
     Kim
    0.06
    úmer
    0.06
    <S
    0.06
     earliest
    0.06
     Aqua
    0.06
     Durch
    0.06
     Sioux
    0.06
     Soros
    0.06
    Kim
    0.06
     UNION
    0.06
    Act Density 0.057%

    No Known Activations