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

    Neuronpedia

    INDEX
    Explanations

    action and emotion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     (
    1.09
     ;-)
    1.07
     നമ്മ
    1.06
     lifecycle
    1.05
    われます
    0.99
    要素
    0.99
    我們會
    0.97
    يزات
    0.97
    ってます
    0.95
     underpin
    0.93
    POSITIVE LOGITS
     hurriedly
    1.50
     angrily
    1.47
     glanced
    1.45
     murmured
    1.44
     trembling
    1.40
     excitedly
    1.39
     startled
    1.36
     motionless
    1.35
     hesitated
    1.35
     слегка
    1.34
    Act Density 0.007%

    No Known Activations