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

    Neuronpedia

    INDEX
    Explanations

    dialogues expressing gratitude and encouragement

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

    Follows words indicating agreement or speech

    np_acts-logits-general · gemini-2.0-flash

    affirmation and declaration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pinulongan
    -0.54
     betweenstory
    -0.48
    CodeAttribute
    -0.47
    PostInfinity
    -0.43
    TintMode
    -0.42
     Paglinawan
    -0.42
    Népesség
    -0.41
    enderror
    -0.41
     attribué
    -0.40
    WarningLevel
    -0.40
    POSITIVE LOGITS
    没问题
    0.59
     agreed
    0.59
    Agreed
    0.58
    Sounds
    0.57
     Agreed
    0.56
    agreed
    0.56
     SUGGEST
    0.55
     agrees
    0.54
     consent
    0.54
     proposal
    0.54
    Act Density 0.222%

    No Known Activations