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

    Neuronpedia

    INDEX
    Explanations

    references to specific terms or entities

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

    subsequent references

    np_acts-logits-general · gemini-2.0-flash

    introducing abbreviations or terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    mbggenerated
    -0.52
    InstrumentedTest
    -0.49
    трите
    -0.40
    EdgeInsets
    -0.40
     tolua
    -0.38
    fug
    -0.38
    いかが
    -0.36
    いかがでしょうか
    -0.36
    횟
    -0.36
    componentDid
    -0.35
    POSITIVE LOGITS
     hereafter
    1.34
     hereinafter
    1.30
     henceforth
    1.11
    hereinafter
    0.92
    以下
    0.89
    ここでは
    0.86
     below
    0.84
     herein
    0.82
    eafter
    0.82
    Below
    0.81
    Act Density 1.315%

    No Known Activations