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

    Neuronpedia

    INDEX
    Explanations

    social media engagement and interactions

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

    like and subscribe

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     للمعارف
    -0.94
    UserScript
    -0.82
    AndEndTag
    -0.77
     autorytatywna
    -0.76
    awtextra
    -0.73
    findpost
    -0.72
    xase
    -0.71
    writeField
    -0.69
    httphttps
    -0.69
    ThroughAttribute
    -0.69
    POSITIVE LOGITS
     голо
    0.35
     rate
    0.28
     subscribe
    0.27
     ved
    0.26
     taux
    0.25
     pl
    0.25
     like
    0.24
     Subscribe
    0.24
     faces
    0.24
    Upvote
    0.24
    Act Density 0.039%

    No Known Activations