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

    Neuronpedia

    INDEX
    Explanations

    the western

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    coord
    0.55
    current
    0.54
    clone
    0.51
    cuenta
    0.51
     अम्ल
    0.49
    format
    0.49
    left
    0.48
    ên
    0.48
    plants
    0.47
    method
    0.47
    POSITIVE LOGITS
    卡通
    0.51
    קום
    0.50
    ковый
    0.50
     व्यस्त
    0.50
     разгово
    0.49
     sost
    0.48
    дитесь
    0.48
     Pavilion
    0.47
     EFL
    0.47
     playthrough
    0.46
    Act Density 0.000%

    No Known Activations