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

    Neuronpedia

    INDEX
    Explanations

    professional background and experience

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     discard
    0.47
     primitives
    0.46
     variables
    0.46
    削除
    0.44
     hideous
    0.44
     删除
    0.43
     parse
    0.42
     discarded
    0.42
     moistened
    0.42
     diminish
    0.42
    POSITIVE LOGITS
     पेशे
    0.64
     профессиона
    0.58
     Expertise
    0.58
     Doctorate
    0.56
    career
    0.56
    経験
    0.55
     specialises
    0.55
     specializes
    0.55
     specializing
    0.55
    出身
    0.55
    Act Density 0.034%

    No Known Activations