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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Comm
    0.74
    comm
    0.64
     Comm
    0.58
    COMM
    0.57
     comm
    0.54
     커
    0.52
    커
    0.52
    com
    0.50
     кому
    0.50
    ocom
    0.49
    POSITIVE LOGITS
     Influ
    0.49
     communications
    0.49
     Communications
    0.48
    Influ
    0.46
     влия
    0.45
     comunicaciones
    0.45
     interactions
    0.44
     передачи
    0.44
     Interactions
    0.44
     connections
    0.44
    Act Density 0.001%

    No Known Activations