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

    Neuronpedia

    INDEX
    Explanations

    understand different

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    à
    0.56
    1
    0.50
     mediante
    0.49
    ementara
    0.48
    urangan
    0.48
    '))
    0.47
     dinast
    0.47
     الي
    0.46
    Usage
    0.46
    Cheese
    0.46
    POSITIVE LOGITS
     Motorsports
    0.46
    لت
    0.46
    нэт
    0.46
     substrates
    0.45
     protocols
    0.45
     techs
    0.44
     တို့
    0.43
    कु
    0.43
     substrate
    0.43
    रेन
    0.43
    Act Density 0.000%

    No Known Activations