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

    Neuronpedia

    INDEX
    Explanations

    references to directories in the content

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

    directory operations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    innocent
    -0.49
    Willem
    -0.48
    mild
    -0.48
     Ră
    -0.47
    catch
    -0.47
    verständlich
    -0.47
    Human
    -0.46
     Willem
    -0.45
    mergeFrom
    -0.45
    Belgian
    -0.45
    POSITIVE LOGITS
     directory
    2.11
    directory
    1.83
     Directory
    1.80
    Directory
    1.60
     DIRECTORY
    1.57
     directories
    1.55
    DIRECTORY
    1.48
    directories
    1.24
    目录
    1.17
     directorio
    1.13
    Act Density 0.005%

    No Known Activations