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

    Neuronpedia

    INDEX
    Explanations

    Text HOME

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     toroidal
    0.52
     velvety
    0.50
     lightness
    0.46
    totalSupply
    0.46
     harmonious
    0.46
    帧
    0.45
    奶油
    0.45
     auctor
    0.43
     primitives
    0.43
    arynge
    0.43
    POSITIVE LOGITS
     tutors
    0.70
     tutoring
    0.69
     मदद
    0.65
     Tutor
    0.65
     tutor
    0.63
     помощ
    0.61
     student
    0.58
     Student
    0.58
     Help
    0.58
     کمک
    0.58
    Act Density 0.077%

    No Known Activations