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

    Neuronpedia

    INDEX
    Explanations

    kindness, support, and values

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     palpable
    0.65
     dynamic
    0.65
     edge
    0.61
     young
    0.60
     condition
    0.60
     collar
    0.59
     tack
    0.59
     anchor
    0.59
     seal
    0.59
    ও
    0.59
    POSITIVE LOGITS
    Justice
    0.75
    Service
    0.74
     Serving
    0.74
     Loot
    0.71
    贡献
    0.70
    Kind
    0.70
    幫助
    0.69
    Serving
    0.69
    善良
    0.69
    服務
    0.68
    Act Density 0.232%

    No Known Activations