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

    Neuronpedia

    INDEX
    Explanations

    specific patterns in programming syntax and structure

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

    legal citations and academic references

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    /**
    -0.55
    RTEX
    -0.54
    MessageOf
    -0.52
    writeFieldEnd
    -0.51
    хьтан
    -0.48
     Савезне
    -0.48
    +#+
    -0.47
    oa̍t
    -0.43
    //
    -0.42
    =".
    -0.41
    POSITIVE LOGITS
     Flat
    0.42
    FXML
    0.40
    pherson
    0.39
     Children
    0.39
     وتسجيلات
    0.39
    __':
    0.37
    AlterField
    0.37
     Kinder
    0.36
    ὶ
    0.35
    Children
    0.34
    Act Density 0.001%

    No Known Activations