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

    Neuronpedia

    INDEX
    Explanations

    memory management

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    కా
    0.44
     SYSTEMS
    0.43
     শাহ
    0.43
     বির
    0.41
    ског
    0.41
     системати
    0.39
     நாய
    0.38
    ශ්‍ය
    0.38
    РИ
    0.37
    ริญ
    0.37
    POSITIVE LOGITS
     includes
    0.49
     contains
    0.48
     __
    0.47
     objects
    0.46
    ?[
    0.45
    nic
    0.44
     include
    0.44
     ->
    0.43
     strongly
    0.43
    contains
    0.40
    Act Density 0.000%

    No Known Activations