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

    Neuronpedia

    INDEX
    Explanations

    relationships, state, acid, transaction, emollient

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    }
    0.45
    umon
    0.45
    county
    0.43
    zej
    0.43
    javac
    0.43
    nah
    0.43
    ຜະລິດຕ
    0.43
    cision
    0.42
    candidate
    0.42
    decimal
    0.42
    POSITIVE LOGITS
    RIBE
    0.52
    لی
    0.49
    LESS
    0.49
    ў
    0.49
    LY
    0.48
    𝗩
    0.48
     penting
    0.47
    LE
    0.47
    ER
    0.47
     ತಪ್ಪ
    0.47
    Act Density 0.002%

    No Known Activations