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

    Neuronpedia

    INDEX
    Explanations

    geographical location and Asia

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     इश्
    0.60
     цвет
    0.57
     źród
    0.54
    цени
    0.54
     měli
    0.54
     武田
    0.53
     stylist
    0.53
     pyaar
    0.53
     intentions
    0.52
    ष्टी
    0.52
    POSITIVE LOGITS
    of
    0.61
    to
    0.59
    q
    0.54
    ş
    0.52
    tr
    0.52
    pm
    0.46
    ໍ
    0.46
    ng
    0.46
    organized
    0.46
    time
    0.44
    Act Density 0.000%

    No Known Activations