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

    Neuronpedia

    INDEX
    Explanations

    in fact

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     которых
    0.50
     которыми
    0.48
     яких
    0.48
     различные
    0.45
     которым
    0.44
    Ways
    0.43
     различными
    0.43
    Whatever
    0.42
    któ
    0.42
    ковым
    0.40
    POSITIVE LOGITS
     fact
    0.61
     Tatsache
    0.54
     neither
    0.51
     fapt
    0.50
     uncharted
    0.49
    cluded
    0.48
     hecho
    0.46
     vain
    0.46
     fato
    0.46
     사실
    0.45
    Act Density 0.022%

    No Known Activations