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

    Neuronpedia

    INDEX
    Explanations

    work experience duration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     باید
    0.75
     we
    0.63
     should
    0.63
     must
    0.63
    者が
    0.61
     ennemis
    0.59
     elkaar
    0.59
     pathologists
    0.58
     ourselves
    0.57
     autres
    0.57
    POSITIVE LOGITS
     करियर
    0.79
    擔任
    0.72
     தனது
    0.71
     mentored
    0.70
     своём
    0.69
     Career
    0.68
     தன்ன
    0.66
     stints
    0.66
    蓴
    0.66
     kendisine
    0.64
    Act Density 0.085%

    No Known Activations