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

    Neuronpedia

    INDEX
    Explanations

    Trevor Project

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    cognitive
    0.42
     Cognitive
    0.41
     Од
    0.41
     Sherman
    0.41
     Fisheries
    0.39
    授業
    0.38
     cognitive
    0.38
    毉
    0.37
    Ϝ
    0.37
    sigs
    0.37
    POSITIVE LOGITS
     projector
    0.56
     Project
    0.55
    Project
    0.54
     Projekt
    0.49
     PROJECT
    0.46
    PROJECT
    0.46
     projectors
    0.46
    project
    0.45
     projekt
    0.43
    Projekt
    0.43
    Act Density 0.004%

    No Known Activations