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

    Neuronpedia

    INDEX
    Explanations

    specific terms

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ificant
    0.67
    Για
    0.67
    加盟
    0.60
     کہا
    0.58
    Said
    0.57
    柜
    0.57
    ரூராட்சி
    0.56
    ର
    0.55
    我说
    0.54
     জিয়া
    0.54
    POSITIVE LOGITS
     poderão
    0.59
     ет
    0.58
     defunct
    0.57
     خواهند
    0.57
     eth
    0.56
     будет
    0.56
     acabado
    0.56
     obligado
    0.56
    終わ
    0.55
     pared
    0.54
    Act Density 0.000%

    No Known Activations