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

    Neuronpedia

    INDEX
    Explanations

    types and specific terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     donnée
    1.99
     bekend
    1.94
    긋
    1.71
     Obat
    1.68
     historians
    1.67
     just
    1.66
    entious
    1.66
    вига
    1.64
     organisers
    1.64
    贻
    1.64
    POSITIVE LOGITS
    thickness
    1.87
     thickness
    1.71
    StudioProjects
    1.70
    breeds
    1.68
    Thickness
    1.63
    breed
    1.58
     siglo
    1.56
     lifecycle
    1.55
    intersection
    1.53
     hour
    1.52
    Act Density 0.114%

    No Known Activations