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 path navigation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    criminator
    -0.48
     achat
    -0.46
    qli
    -0.46
    straint
    -0.45
    adget
    -0.45
     dieß
    -0.44
    riwal
    -0.44
     polig
    -0.43
     ſche
    -0.41
     pegat
    -0.41
    POSITIVE LOGITS
     '../
    2.11
     "../
    1.89
     '../../
    1.66
     "../../
    1.52
    ('../
    1.52
     './../
    1.50
     '../../../
    1.46
    ("../
    1.45
    "../
    1.34
     "../../../
    1.29
    Act Density 0.001%

    No Known Activations