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

    Neuronpedia

    INDEX
    Explanations

    words ending in 'and'

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    niejszych
    0.44
    nington
    0.40
    attuale
    0.39
    endl
    0.38
    endid
    0.38
    nette
    0.38
    niji
    0.38
    endre
    0.38
    adati
    0.37
    idency
    0.37
    POSITIVE LOGITS
    ees
    0.53
    orf
    0.51
    olph
    0.50
    ер
    0.49
    scaping
    0.49
    wiches
    0.48
    scapes
    0.48
    amental
    0.47
    ezza
    0.46
    ependence
    0.46
    Act Density 0.025%

    No Known Activations