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

    Neuronpedia

    INDEX
    Explanations

    phrases related to ratings, evaluations, and statistical measures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    fractions and percentages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    MigrationBuilder
    -0.52
     PeEnEo
    -0.49
    -0.43
    цездатний
    -0.41
     enfans
    -0.40
    ➌
    -0.40
     män
    -0.40
    ❋
    -0.40
    Referencies
    -0.39
     ویکی‌پدی
    -0.38
    POSITIVE LOGITS
     among
    0.61
     parmi
    0.54
     amongst
    0.52
    among
    0.51
    ⅗
    0.50
     מתוך
    0.47
     blant
    0.47
     среди
    0.46
     ModelRenderer
    0.45
    ">—
    0.44
    Act Density 0.139%

    No Known Activations