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

    Neuronpedia

    INDEX
    Explanations

    occupational and career codes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sucked
    0.43
     suck
    0.42
     consumo
    0.42
     nég
    0.42
     aliases
    0.39
     whatever
    0.39
     useless
    0.39
     यस
    0.38
     agencia
    0.38
     احنا
    0.38
    POSITIVE LOGITS
     occupations
    0.66
     occupation
    0.64
     occupational
    0.63
     Occupation
    0.61
     Occupational
    0.58
    occupation
    0.57
    Occupation
    0.56
     Vocational
    0.51
    occup
    0.47
     managerial
    0.47
    Act Density 0.010%

    No Known Activations