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

    Neuronpedia

    INDEX
    Explanations

    features and functionalities related to comment moderation in an online forum

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

    comment viewing options

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     utafitiHapana
    -0.78
    rungsseite
    -0.68
     فريبيس
    -0.67
    yntaxException
    -0.65
    Xna
    -0.65
     nahilalakip
    -0.63
    دانشنامهٔ
    -0.63
    MigrationBuilder
    -0.60
    setVerticalGroup
    -0.59
    HostException
    -0.59
    POSITIVE LOGITS
     comment
    0.76
     comments
    0.74
    comment
    0.61
    comments
    0.59
     Comments
    0.57
     feedback
    0.56
     comentarios
    0.56
     Comment
    0.55
    comentarios
    0.54
     remarks
    0.52
    Act Density 0.061%

    No Known Activations