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

    Neuronpedia

    INDEX
    Explanations

    ambient sounds and gentle modifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     auditory
    0.68
     listening
    0.67
     Hearing
    0.61
     Listening
    0.61
     ascol
    0.61
    Listening
    0.59
     سننے
    0.59
     ear
    0.58
     listen
    0.58
     listened
    0.58
    POSITIVE LOGITS
     footsteps
    0.88
     shuffling
    0.66
    脚步
    0.65
     sighs
    0.58
     laughter
    0.57
     Schritte
    0.57
     crunch
    0.57
     gunfire
    0.56
     ticking
    0.55
     shuffle
    0.53
    Act Density 0.023%

    No Known Activations