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

    Neuronpedia

    INDEX
    Explanations

    expert in a field

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     loaf
    0.47
     simple
    0.47
     loaves
    0.47
     default
    0.46
    Allowed
    0.46
     burning
    0.45
     basic
    0.45
     darkening
    0.45
     사람들
    0.44
     use
    0.44
    POSITIVE LOGITS
     экспер
    1.13
     consultant
    1.11
     expert
    1.09
     ماہر
    1.06
     experto
    1.05
     специалист
    1.02
     Consultant
    0.99
     psychologist
    0.96
     nutritionist
    0.96
     journalist
    0.93
    Act Density 0.023%

    No Known Activations