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

    Neuronpedia

    INDEX
    Explanations

    styles of living

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    O
    0.80
    E
    0.77
    P
    0.77
    وم
    0.75
    F
    0.72
    ס
    0.70
    International
    0.68
    Group
    0.67
    S
    0.67
    C
    0.67
    POSITIVE LOGITS
     LIVING
    0.75
    ные
    0.69
    ный
    0.64
    нда
    0.64
     elevado
    0.64
    क्षा
    0.64
     Living
    0.64
    ных
    0.63
    living
    0.63
    urare
    0.63
    Act Density 0.006%

    No Known Activations