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

    Neuronpedia

    INDEX
    Explanations

    adjectives followed by nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sneaky
    1.15
     blurry
    1.14
     crispy
    1.11
     langfrist
    1.10
     scary
    1.05
     shiny
    1.05
     starken
    1.03
     lazy
    1.03
     fluffy
    1.01
     wacky
    1.00
    POSITIVE LOGITS
     demurrer
    0.84
     reckoning
    0.78
     censure
    0.77
    எ
    0.74
     reckon
    0.73
    omenclature
    0.72
     оборо
    0.72
    acqu
    0.71
     measure
    0.69
     remon
    0.69
    Act Density 0.267%

    No Known Activations