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

    Neuronpedia

    INDEX
    Explanations

    words that express appreciation or admiration

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

    Positive feedback or congratulations

    np_acts-logits-general · gemini-2.0-flash

    praise and positive commentary

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     believe
    -0.58
     believes
    -0.57
    mybatisplus
    -0.55
    iole
    -0.55
    Alguna
    -0.54
     believing
    -0.53
    rego
    -0.52
     approximately
    -0.50
    جوم
    -0.48
    )}{\
    -0.48
    POSITIVE LOGITS
    horabuena
    0.91
    congrats
    0.74
     congrats
    0.71
     Congrats
    0.69
    Nice
    0.67
    lovely
    0.66
     👏
    0.64
    Congrats
    0.61
    wonderful
    0.61
     nice
    0.61
    Act Density 0.128%

    No Known Activations