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

    Neuronpedia

    INDEX
    Explanations

    postal codes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ৩২
    0.47
    meden
    0.43
    ki
    0.43
    hp
    0.43
     eighty
    0.42
     seventy
    0.42
    Twelve
    0.42
    Forty
    0.42
    ৪১
    0.42
    dai
    0.42
    POSITIVE LOGITS
    OMG
    0.44
    郵便
    0.41
     OMG
    0.40
     OG
    0.40
    零
    0.39
    ാമ
    0.38
    讓人
    0.38
     ODE
    0.38
    ਾਲ
    0.37
     తగ్
    0.37
    Act Density 0.002%

    No Known Activations