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

    Neuronpedia

    INDEX
    Explanations

    bouncing the ball

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    其他
    0.63
     dobr
    0.62
     gemäß
    0.61
     huyện
    0.60
    g
    0.59
    efic
    0.58
     obvi
    0.57
    gab
    0.57
    ामुळे
    0.56
    ণ
    0.56
    POSITIVE LOGITS
    ৭
    0.85
     loneliness
    0.79
     whispers
    0.76
     glimpse
    0.75
    ১
    0.74
     nourishing
    0.73
     arrogance
    0.73
     élég
    0.72
     soulful
    0.72
    場所に
    0.71
    Act Density 0.001%

    No Known Activations