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

    Neuronpedia

    INDEX
    Explanations

    urgency, augmentation, collaborative, iterative, recognize, escalates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     bandana
    0.66
     measles
    0.64
     ukuran
    0.63
     zehn
    0.63
     platter
    0.62
     zenith
    0.61
     shrimp
    0.59
     vile
    0.59
     flap
    0.59
     olla
    0.59
    POSITIVE LOGITS
    로운
    0.74
    ing
    0.72
    <unused410>
    0.66
    iovascular
    0.63
    ic
    0.62
    IoT
    0.62
    ㎿
    0.62
    Ак
    0.61
    ہ
    0.61
    <unused717>
    0.61
    Act Density 1.218%

    No Known Activations