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

    Neuronpedia

    INDEX
    Explanations

    But followed by contrasting adjectives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     segmentation
    0.47
     corral
    0.45
     brochure
    0.45
     TCM
    0.44
     lactose
    0.44
     pamphlets
    0.42
     spout
    0.41
     Deuteronomy
    0.41
     brochures
    0.41
     scont
    0.40
    POSITIVE LOGITS
    and
    0.52
    registrer
    0.52
    lier
    0.44
    או
    0.44
    Lire
    0.43
    ändern
    0.41
     dém
    0.41
    rů
    0.41
    ant
    0.41
    đ
    0.41
    Act Density 0.001%

    No Known Activations