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

    Neuronpedia

    INDEX
    Explanations

    n <=, ml, data, Pico, not

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Organic
    0.50
    ROY
    0.45
    Occupation
    0.44
    Quotes
    0.44
    Article
    0.44
    Volume
    0.43
    Earnings
    0.43
     quotations
    0.43
    Individuals
    0.42
    GED
    0.41
    POSITIVE LOGITS
     herzlich
    0.49
     காலநிலை
    0.47
     کے
    0.46
    rün
    0.46
     çeşit
    0.46
     के
    0.45
     frail
    0.45
     estudios
    0.45
     និង
    0.44
     asexual
    0.44
    Act Density 0.001%

    No Known Activations