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

    Neuronpedia

    INDEX
    Explanations

    mentoring and leadership

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     willst
    0.40
     quieres
    0.39
     hammers
    0.38
     slur
    0.37
     délai
    0.37
     zależności
    0.37
     exploded
    0.35
     witches
    0.35
     hammer
    0.34
     gul
    0.34
    POSITIVE LOGITS
     mentor
    0.85
     mentoring
    0.77
     leadership
    0.74
     mentors
    0.72
     активно
    0.71
     актив
    0.71
    Leadership
    0.71
    leadership
    0.70
     Mentor
    0.70
     mentorship
    0.70
    Act Density 0.008%

    No Known Activations