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

    Neuronpedia

    INDEX
    Explanations

    penthouse apartment ballroom

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    that
    1.10
    m
    1.04
    м
    0.99
    ار
    0.97
    1
    0.94
    j
    0.90
    he
    0.88
    ada
    0.88
    ود
    0.85
    ü
    0.85
    POSITIVE LOGITS
    。...
    0.89
    𝘪
    0.78
    :...
    0.76
     for
    0.76
    $...
    0.73
     foreshadow
    0.72
     불구하고
    0.72
    。
    0.70
     ją
    0.70
    -...
    0.70
    Act Density 0.000%

    No Known Activations