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

    Neuronpedia

    INDEX
    Explanations

    names of people

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     uygulan
    0.74
    స్తాయి
    0.73
     Denote
    0.72
     entail
    0.70
     afectan
    0.67
    Require
    0.67
     ఉంటాయి
    0.67
    使其
    0.67
    டுகின்றன
    0.66
     만드는
    0.64
    POSITIVE LOGITS
     was
    1.74
     knew
    1.63
     had
    1.63
     wasn
    1.46
     began
    1.42
     didn
    1.40
     took
    1.40
     went
    1.35
     gave
    1.34
     waited
    1.34
    Act Density 0.237%

    No Known Activations