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

    Neuronpedia

    INDEX
    Explanations

    career paths and pursuits

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    encode
    0.41
     ricotta
    0.41
     encode
    0.40
     momentos
    0.39
    zza
    0.39
     Experiment
    0.39
     experiment
    0.39
     affez
    0.38
    resin
    0.38
     Experiments
    0.37
    POSITIVE LOGITS
     career
    1.80
     careers
    1.73
    career
    1.70
    Career
    1.69
     Career
    1.60
     करियर
    1.54
    Careers
    1.54
     carreira
    1.50
    careers
    1.49
     Careers
    1.48
    Act Density 0.035%

    No Known Activations