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

    Neuronpedia

    INDEX
    Explanations

    stream collect map filter

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    raltar
    0.47
     تلق
    0.43
    Celltype
    0.41
    Automatically
    0.41
     자동으로
    0.40
     खुदाई
    0.40
    opcode
    0.40
    readthedocs
    0.39
     rutin
    0.39
     অক্সিজেন
    0.38
    POSITIVE LOGITS
     collecting
    0.84
     stream
    0.83
    Stream
    0.79
    collect
    0.77
     filtering
    0.77
    Collect
    0.74
     collect
    0.73
    stream
    0.73
     Stream
    0.71
    收集
    0.70
    Act Density 0.014%

    No Known Activations