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

    Neuronpedia

    INDEX
    Explanations

    feeling compelled or pressured

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Being
    0.31
     étant
    0.29
     BEING
    0.29
     Seorang
    0.28
     sendo
    0.27
     being
    0.27
    Being
    0.26
     beings
    0.26
     alguien
    0.26
    泹
    0.25
    POSITIVE LOGITS
     like
    0.50
     tempted
    0.41
     compelled
    0.38
     embarrassed
    0.36
     ashamed
    0.34
     torn
    0.34
     intimidated
    0.34
     paralyzed
    0.34
     confused
    0.33
     choked
    0.33
    Act Density 0.009%

    No Known Activations