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

    Neuronpedia

    INDEX
    Explanations

    scientific studies

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     arrows
    -0.07
    usty
    -0.06
     कथ
    -0.06
    rikes
    -0.06
     Eth
    -0.06
    ogl
    -0.06
    iefs
    -0.06
    充
    -0.06
    Unique
    -0.06
    कर
    -0.06
    POSITIVE LOGITS
    realloc
    0.07
    tributes
    0.07
    .validation
    0.07
    iveau
    0.06
    seau
    0.06
    ジ
    0.06
    стати
    0.06
    ดย
    0.06
     일정
    0.06
     एज
    0.06
    Act Density 0.129%

    No Known Activations