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

    Neuronpedia

    INDEX
    Explanations

    negative symbols or statements typically used in coding contexts

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

    μm, mg

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     purpoſe
    -0.59
     deſt
    -0.57
     ſever
    -0.57
    帖最后由
    -0.57
     laſt
    -0.57
     ſtate
    -0.55
     fubject
    -0.55
     occaf
    -0.55
    sizeCache
    -0.54
     ſta
    -0.54
    POSITIVE LOGITS
     [*]
    0.67
     <<<<<<<<<<<<<<
    0.49
     popoli
    0.41
    httphttps
    0.40
     Geografia
    0.40
     initComponents
    0.40
     للمعارف
    0.38
    NewReader
    0.36
    回
    0.35
    SneakyThrows
    0.34
    Act Density 0.377%

    No Known Activations