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

    Neuronpedia

    INDEX
    Explanations

    conducting surveys

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     survey
    1.02
    survey
    0.91
     surveys
    0.84
     Surveys
    0.82
     surveyed
    0.81
     SURVEY
    0.80
     Survey
    0.77
     surveying
    0.72
    Survey
    0.72
     surveyor
    0.72
    POSITIVE LOGITS
    Monkey
    0.67
     monkey
    0.65
     administered
    0.52
     shipped
    0.52
    rightbar
    0.52
     Monkey
    0.51
     takers
    0.50
     instruments
    0.49
     instrument
    0.46
    Sent
    0.45
    Act Density 0.005%

    No Known Activations