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

    Neuronpedia

    INDEX
    Explanations

    immediately / **

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     financiación
    0.59
     fruitless
    0.52
     financi
    0.52
     fuselage
    0.51
     районов
    0.50
    ям
    0.49
    عة
    0.48
     rotational
    0.47
     финанси
    0.47
     carbonyl
    0.47
    POSITIVE LOGITS
    Run
    0.53
     Run
    0.46
    Якщо
    0.46
    RT
    0.45
    Hvis
    0.45
    Deliver
    0.44
    KeyValue
    0.44
    N
    0.43
    Tcp
    0.43
    LP
    0.43
    Act Density 0.003%

    No Known Activations