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

    Neuronpedia

    INDEX
    Explanations

    numerical quantities and statistics

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

    Fractions (thirds, fifths, half)

    np_acts-logits-general · gemini-2.0-flash

    Fractions and ordinals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kaynağından
    -0.49
    قایناق‌لار
    -0.47
     <<<<<<<<<<<<<<
    -0.46
     leksikon
    -0.44
     encara
    -0.44
    RepeatedField
    -0.43
    PropertyChanging
    -0.43
    mybatisplus
    -0.42
     réflex
    -0.41
    گانی
    -0.41
    POSITIVE LOGITS
     thirds
    0.87
     third
    0.82
     fifth
    0.81
     fourth
    0.79
    third
    0.78
    Third
    0.76
     Third
    0.75
     FIFTH
    0.75
     ninth
    0.73
    fifth
    0.73
    Act Density 0.558%

    No Known Activations