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

    Neuronpedia

    INDEX
    Explanations

    phone numbers and country codes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ،
    0.53
    0.49
    ，
    0.43
     </
    0.41
    }}
    0.40
    、
    0.40
    ፣
    0.40
     Lä
    0.39
    ופ
    0.38
     \\
    0.38
    POSITIVE LOGITS
    is
    0.44
     bienvenidos
    0.37
     দুর্বল
    0.35
    periode
    0.35
    ud
    0.35
    iden
    0.35
     তৈরি
    0.34
    ombe
    0.34
     منظم
    0.34
    matism
    0.34
    Act Density 0.000%

    No Known Activations