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

    Neuronpedia

    INDEX
    Explanations

    foot traffic and actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     barefoot
    0.60
     feet
    0.57
    👣
    0.57
     Feet
    0.54
    脚
    0.52
     piedi
    0.52
     pieds
    0.49
    🦵
    0.48
     Walking
    0.47
    腳
    0.47
    POSITIVE LOGITS
    익
    0.38
    burse
    0.36
    "
    0.36
     perish
    0.36
    Iv
    0.36
    수로
    0.35
     Frem
    0.35
    зья
    0.35
    場
    0.35
    針
    0.35
    Act Density 0.003%

    No Known Activations