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

    Neuronpedia

    INDEX
    Explanations

    references to academic citations and methodologies

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

    publications

    np_acts-logits-general · gemini-2.0-flash

    academic references

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     defaultstate
    -0.42
    aarrggbb
    -0.41
     Füße
    -0.39
    windowFixed
    -0.39
     Topf
    -0.38
    şört
    -0.38
    éndolo
    -0.37
     griega
    -0.37
     kald
    -0.36
     fenô
    -0.36
    POSITIVE LOGITS
     Ref
    1.23
     Reference
    1.12
     ref
    1.10
     reference
    1.09
     Refs
    1.07
     refs
    1.05
    Ref
    1.01
     REFERENCE
    1.00
    reference
    0.99
     references
    0.98
    Act Density 2.060%

    No Known Activations