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

    Neuronpedia

    INDEX
    Explanations

    describing action, state, or quality

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     hospitals
    0.46
     can
    0.45
     affiliates
    0.45
     \
    0.45
    ก
    0.45
    t
    0.45
     uninformed
    0.44
    내
    0.44
     ASME
    0.44
     Algonquin
    0.44
    POSITIVE LOGITS
    :
    0.52
    7
    0.50
    ue
    0.48
    iva
    0.48
    lem
    0.47
    </h2>
    0.47
    itionen
    0.46
    gem
    0.45
     handelt
    0.45
    8
    0.45
    Act Density 0.786%

    No Known Activations