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

    Neuronpedia

    INDEX
    Explanations

    emotional responses and expressions of opinion

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

    Beginning of sarcastic remarks or rhetorical questions

    np_acts-logits-general · gemini-2.0-flash

    interjections and commands

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     empleos
    -0.41
     Públicas
    -0.41
    MessageOf
    -0.40
    nocześnie
    -0.37
     miesięcy
    -0.36
     Bitte
    -0.35
     Mitgliedern
    -0.35
    ----</
    -0.35
     devido
    -0.35
     veuillez
    -0.35
    POSITIVE LOGITS
     ZAP
    0.55
    ochlor
    0.54
    Chalk
    0.53
    forks
    0.52
     ditto
    0.52
     chalk
    0.52
     Cue
    0.52
    EndProject
    0.52
     Ditto
    0.52
    orino
    0.52
    Act Density 0.348%

    No Known Activations