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

    Neuronpedia

    INDEX
    Explanations

    emotional states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ChangeListener
    0.38
     Mastering
    0.37
     Incident
    0.36
     کمک
    0.34
     oor
    0.33
     поможет
    0.33
    幫
    0.33
     מדי
    0.33
     هل
    0.32
     производится
    0.32
    POSITIVE LOGITS
     feel
    1.06
     feels
    0.97
    feel
    0.96
     felt
    0.95
     чув
    0.93
     merasa
    0.88
    感じ
    0.86
     відчу
    0.86
    Feel
    0.84
    feels
    0.83
    Act Density 0.053%

    No Known Activations