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

    Neuronpedia

    INDEX
    Explanations

    contextual reasoning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ò
    0.48
     thankfully
    0.48
    ColumnCount
    0.46
    மனித
    0.45
     can
    0.44
    ürlich
    0.44
    ith
    0.43
    ư
    0.43
    è
    0.42
    ión
    0.42
    POSITIVE LOGITS
    成分
    0.48
    小題
    0.46
     issuer
    0.46
     হাজির
    0.45
     maturities
    0.45
     underwriting
    0.43
     komponent
    0.43
     demographics
    0.43
    入手
    0.42
     бир
    0.42
    Act Density 0.000%

    No Known Activations