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

    Neuronpedia

    INDEX
    Explanations

    domains and email addresses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     penalties
    0.40
     पहलुओं
    0.40
    世界
    0.39
     protection
    0.38
    wearing
    0.38
    বাজার
    0.38
    ការពារ
    0.37
     دنیا
    0.37
    nyc
    0.37
    foot
    0.37
    POSITIVE LOGITS
     }\
    0.39
     கூ
    0.37
    امی
    0.37
    iacute
    0.35
     Detta
    0.35
     Acute
    0.34
    र्जर
    0.34
     Surface
    0.34
     Ricardo
    0.34
     suces
    0.34
    Act Density 0.028%

    No Known Activations