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

    Neuronpedia

    INDEX
    Explanations

    checking not null or not equal

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     যাইত
    0.44
     어려운
    0.43
    LLCATS
    0.40
    反而
    0.39
    धिक
    0.38
     undermines
    0.38
    <start_of_turn>
    0.38
    会导致
    0.38
    ানের
    0.37
     paraissent
    0.37
    POSITIVE LOGITS
     !=
    0.74
    !=
    0.67
     isn
    0.62
    NotNull
    0.61
     !==
    0.57
    !==
    0.54
     null
    0.54
    isNotEmpty
    0.52
     nullptr
    0.50
     bukan
    0.50
    Act Density 0.025%

    No Known Activations