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

    Neuronpedia

    INDEX
    Explanations

    inquiries about personal experiences and expectations

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

    Following pronouns and auxiliary verbs

    np_acts-logits-general · gemini-2.0-flash

    what has been done or learned

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    contentLoaded
    -0.65
    DockStyle
    -0.61
    PROLOG
    -0.57
    ApplicationTests
    -0.57
    raszamy
    -0.56
     alfab
    -0.54
    rawDesc
    -0.52
    JsonFormat
    -0.51
    PANY
    -0.51
     AssemblyCompany
    -0.51
    POSITIVE LOGITS
     accomplished
    0.75
     accomplish
    0.71
    Accomplished
    0.64
     allemaal
    0.59
    seamnă
    0.57
     achieved
    0.56
     done
    0.56
     glean
    0.55
     learned
    0.54
    complished
    0.53
    Act Density 0.164%

    No Known Activations