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

    Neuronpedia

    INDEX
    Explanations

    input_shape and activation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Mineral
    0.42
    ihal
    0.40
    ⵖ
    0.40
    LOT
    0.39
    objClass
    0.39
    eppo
    0.38
     collie
    0.38
    ธาร
    0.38
    dataPro
    0.38
    ံ
    0.38
    POSITIVE LOGITS
     blank
    0.71
     help
    0.67
     Blank
    0.63
     null
    0.63
    blank
    0.62
     verbose
    0.62
    help
    0.57
    null
    0.56
    Blank
    0.55
    verbose
    0.54
    Act Density 0.006%

    No Known Activations