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

    Neuronpedia

    INDEX
    Explanations

    references to directories or directory structures

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

    directory contents or listing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Wanna
    -0.53
    Obama
    -0.51
     Ră
    -0.50
     climático
    -0.48
    Kobe
    -0.48
    Hung
    -0.48
    Sean
    -0.48
    said
    -0.48
    Human
    -0.47
    Konst
    -0.47
    POSITIVE LOGITS
     directory
    1.15
     Directory
    1.06
    directory
    1.02
    Directory
    1.01
     DIRECTORY
    0.96
    DIRECTORY
    0.95
     directories
    0.89
    directories
    0.81
    isDirectory
    0.76
    Directories
    0.70
    Act Density 0.005%

    No Known Activations