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

    Neuronpedia

    INDEX
    Explanations

    voice cloning or woolens

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Destinations
    0.61
     Mitarbeit
    0.60
     bestselling
    0.60
     Überblick
    0.59
     Workflow
    0.59
     Entsche
    0.57
     Candidates
    0.56
     лучших
    0.56
     erstellt
    0.56
     eponymous
    0.55
    POSITIVE LOGITS
     inflammation
    0.70
     malnutrition
    0.68
     ulcers
    0.68
     inhalation
    0.68
    皮肤
    0.67
     irritability
    0.66
     discoloration
    0.66
     corticoster
    0.63
     rashes
    0.63
     ventilation
    0.63
    Act Density 5.713%

    No Known Activations