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

    Neuronpedia

    INDEX
    Explanations

    roles of leader or helper

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sulfates
    0.72
     halides
    0.71
    yoga
    0.71
    olids
    0.71
    oplastics
    0.71
     जिन
    0.70
    TextChanged
    0.70
    浃
    0.69
    ্বাস
    0.69
    ocy
    0.68
    POSITIVE LOGITS
     mediator
    1.95
     arbitrator
    1.95
     protector
    1.90
     guardian
    1.89
     executor
    1.78
     coordinator
    1.76
     maestro
    1.75
     savior
    1.74
     playmaker
    1.73
     supervisor
    1.72
    Act Density 0.594%

    No Known Activations