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

    Neuronpedia

    INDEX
    Explanations

    file paths or references to directories in code

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

    relative file paths

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     enfans
    -0.49
     recevrez
    -0.48
     habet
    -0.45
     avoient
    -0.45
     народов
    -0.43
     brille
    -0.41
     âmes
    -0.41
     amplification
    -0.41
     Gleaner
    -0.41
    assination
    -0.40
    POSITIVE LOGITS
     ['./
    0.98
     ./
    0.94
    ="./
    0.91
    ("./
    0.78
     AssemblyVersion
    0.77
     "./
    0.77
    "./
    0.75
    ./
    0.74
     './
    0.74
     './../
    0.74
    Act Density 0.002%

    No Known Activations