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

    Neuronpedia

    INDEX
    Explanations

    let me know

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     recognising
    0.49
     conversation
    0.45
     understanding
    0.44
     trusts
    0.42
     recognition
    0.42
     conversa
    0.40
     entendimento
    0.40
     discussing
    0.40
     recognizing
    0.40
    Understanding
    0.40
    POSITIVE LOGITS
     know
    0.63
     Know
    0.56
    Know
    0.52
     знает
    0.50
     знать
    0.49
    know
    0.47
    知
    0.47
     Knows
    0.46
     знают
    0.43
     conoce
    0.42
    Act Density 0.003%

    No Known Activations