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

    Neuronpedia

    INDEX
    Explanations

    quantitative data regarding percentages and statistical proportions

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

    Numbers followed by units or other identifiers

    np_acts-logits-general · gemini-2.0-flash

    percentages and counts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    '):
    -0.61
    ++)
    -0.58
     &&
    -0.55
    --)
    -0.54
    '>
    -0.53
    ++
    -0.53
    SharedCtor
    -0.52
    AutoField
    -0.52
    ":"+
    -0.51
    []
    -0.51
    POSITIVE LOGITS
     یعنی
    0.88
     yani
    0.81
     czyli
    0.81
    也就是
    0.80
     ovvero
    0.80
     amounting
    0.78
     cioè
    0.78
     ossia
    0.75
     (~
    0.74
     soit
    0.74
    Act Density 0.327%

    No Known Activations