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

    Neuronpedia

    INDEX
    Explanations

    specialization and specialists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    总结
    0.46
    钗
    0.41
    世代
    0.41
    ske
    0.41
    缥
    0.41
    బ్బు
    0.40
    stol
    0.40
    vole
    0.39
    Little
    0.39
    pais
    0.38
    POSITIVE LOGITS
     специали
    0.63
     Specialist
    0.63
     knowledge
    0.61
     specialist
    0.61
     spécialistes
    0.60
     specialization
    0.59
     Specialists
    0.57
     spécialiste
    0.56
     specialists
    0.55
     specialty
    0.55
    Act Density 0.008%

    No Known Activations