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

    Neuronpedia

    INDEX
    Explanations

    drawn to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    招
    0.46
    บน
    0.44
    孟
    0.42
    讨
    0.40
    拄
    0.40
    注目
    0.39
    akura
    0.39
     получает
    0.39
     commandant
    0.39
     внимание
    0.38
    POSITIVE LOGITS
     gravitate
    1.16
     grav
    1.04
     Grav
    0.95
     drawn
    0.91
     gravit
    0.91
    grav
    0.90
    Grav
    0.85
     gravitation
    0.76
    drawn
    0.75
     Drawn
    0.74
    Act Density 0.020%

    No Known Activations