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

    Neuronpedia

    INDEX
    Explanations

    circumstances and relations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Filing
    0.38
     Market
    0.38
    </td>
    0.37
     Sébastien
    0.37
     Central
    0.37
     Reset
    0.37
    yn
    0.36
    reset
    0.36
     Select
    0.36
     Çünkü
    0.36
    POSITIVE LOGITS
     совокуп
    0.52
    굉
    0.51
     uwagę
    0.48
     circumst
    0.46
     obesidad
    0.45
     circumstances
    0.45
     alkohol
    0.45
    troops
    0.45
     продолжи
    0.44
     longueur
    0.44
    Act Density 0.004%

    No Known Activations