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

    Neuronpedia

    INDEX
    Explanations

    writing to express interest

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     distribuzione
    0.46
     devons
    0.45
    再
    0.44
    ouched
    0.44
     টন
    0.43
    均匀
    0.43
    制
    0.43
     halten
    0.42
    刪
    0.42
     fooled
    0.42
    POSITIVE LOGITS
     candidacy
    0.67
     candidature
    0.63
     confident
    0.57
     candidate
    0.55
     enthusiasm
    0.52
     candidatura
    0.52
     entusiasmo
    0.52
     qualities
    0.49
     enthusiastic
    0.49
     applicant
    0.49
    Act Density 0.100%

    No Known Activations