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

    Neuronpedia

    INDEX
    Explanations

    "`below` followed by verb"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     herein
    0.49
     burada
    0.43
     hereunder
    0.41
    Park
    0.40
    Centro
    0.40
    0.40
     officinalis
    0.40
    Responsibilities
    0.39
    Pool
    0.39
     Nauchno
    0.39
    POSITIVE LOGITS
     তেমনই
    0.59
    어를
    0.44
     এমন
    0.42
    ávají
    0.42
    тся
    0.40
    ન્ડ
    0.40
    ခြား
    0.40
    ूर
    0.39
    ដើ
    0.39
    चीन
    0.39
    Act Density 0.000%

    No Known Activations