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

    Neuronpedia

    INDEX
    Explanations

    harmful stereotypes, control, objectify

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     recent
    0.38
     intolerance
    0.35
     Elements
    0.35
     ceases
    0.34
     needs
    0.34
     survey
    0.34
     surve
    0.34
     terminus
    0.34
    DisplayStyle
    0.33
     CI
    0.33
    POSITIVE LOGITS
     deportivos
    0.43
    娱乐
    0.43
     pese
    0.41
     سپورټ
    0.41
     Versorgung
    0.41
    ेंजर
    0.41
    licher
    0.40
    쳐
    0.39
    ബി
    0.39
    lej
    0.39
    Act Density 0.000%

    No Known Activations