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

    Neuronpedia

    INDEX
    Explanations

    locations followed by state or country

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    arounds
    0.38
    least
    0.38
    ength
    0.38
    ታት
    0.37
    辊
    0.37
     answers
    0.37
    insc
    0.36
    ("
    0.36
     flies
    0.36
    (...
    0.36
    POSITIVE LOGITS
     ktorí
    0.44
    美國
    0.43
     naturalmente
    0.42
     október
    0.42
     October
    0.41
     naturellement
    0.41
     którzy
    0.40
     vốn
    0.40
     često
    0.40
     conocida
    0.40
    Act Density 0.000%

    No Known Activations