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

    Neuronpedia

    INDEX
    Explanations

    Technical context

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    mensagem
    0.92
     mensagens
    0.89
    messages
    0.86
     message
    0.84
    eur
    0.84
     messages
    0.83
    RL
    0.83
    message
    0.83
     ܗ
    0.82
    texte
    0.82
    POSITIVE LOGITS
    MONTH
    0.77
    ोषित
    0.74
     Temp
    0.73
    Step
    0.72
    我相信
    0.70
     ขั้น
    0.70
     temp
    0.70
    競馬
    0.69
    Day
    0.67
     διάρκ
    0.67
    Act Density 0.000%

    No Known Activations