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

    Neuronpedia

    INDEX
    Explanations

    positive feedback or evaluations of content

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

    Follows positive adjectives/interjections

    np_acts-logits-general · gemini-2.0-flash

    positive evaluations and content

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     للاسماء
    -0.74
    /*++
    -0.73
    seamnă
    -0.69
    EndProject
    -0.68
    onAttach
    -0.66
    DockStyle
    -0.65
     getItemId
    -0.64
    ForValue
    -0.62
    delwed
    -0.62
     termica
    -0.61
    POSITIVE LOGITS
     job
    0.95
     idea
    0.90
     work
    0.78
     choice
    0.78
     stuff
    0.73
     news
    0.72
     decision
    0.70
     concept
    0.68
     evening
    0.67
     timing
    0.67
    Act Density 0.113%

    No Known Activations