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

    Neuronpedia

    INDEX
    Explanations

    along the way and with

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     বাঙ্গাল
    0.41
    嵐
    0.41
    يه
    0.40
    ക്കുറ
    0.39
     Subcommittee
    0.38
     వ్యవ
    0.38
    SubSystem
    0.38
    ampe
    0.38
    iliency
    0.38
     Gosudarstvennyj
    0.38
    POSITIVE LOGITS
     along
    1.01
    along
    0.83
     entlang
    0.82
     вдоль
    0.82
     coastline
    0.81
    沿
    0.78
     path
    0.75
    Along
    0.73
     rivers
    0.71
     shoreline
    0.71
    Act Density 0.019%

    No Known Activations