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

    Neuronpedia

    INDEX
    Explanations

    references to roles in educational or professional contexts

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

    training, interns, teachers, students

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AndEndTag
    -0.52
    Javadoc
    -0.50
    ectady
    -0.45
    awtextra
    -0.44
     fince
    -0.44
    PreferredItem
    -0.44
    achios
    -0.42
    lwz
    -0.41
     Solaris
    -0.41
    URLException
    -0.40
    POSITIVE LOGITS
     internship
    0.46
    лтемелер
    0.41
     hem
    0.40
     internships
    0.40
    GHIJKLM
    0.39
    VIAF
    0.38
    contentLoaded
    0.38
     intern
    0.37
     unknownFields
    0.36
     semester
    0.36
    Act Density 0.014%

    No Known Activations