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

    Neuronpedia

    INDEX
    Explanations

    names of people and places

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Susan
    0.49
    Susan
    0.44
    Barbara
    0.43
     Barbara
    0.43
     Women
    0.42
     ACLU
    0.42
     Smithsonian
    0.39
     Woman
    0.39
     Sisters
    0.39
     Margaret
    0.38
    POSITIVE LOGITS
     Ичиго
    0.46
    <unused369>
    0.43
    <unused602>
    0.40
    <unused415>
    0.40
    <unused465>
    0.38
     consistente
    0.38
    <unused481>
    0.38
    <unused2121>
    0.38
    एंड
    0.37
     Zidane
    0.37
    Act Density 0.042%

    No Known Activations