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

    Neuronpedia

    INDEX
    Explanations

    name, ID, columns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Limits
    0.54
    для
    0.54
     prototyping
    0.52
    তিন
    0.51
     গোল
    0.50
    からない
    0.50
     limites
    0.49
     специализирован
    0.48
    calculator
    0.48
     límites
    0.48
    POSITIVE LOGITS
     name
    1.05
    name
    0.97
    Name
    0.96
     Name
    0.96
    姓名
    0.94
     navn
    0.91
     namn
    0.82
     nombre
    0.80
     이름
    0.80
     పేరు
    0.79
    Act Density 0.449%

    No Known Activations