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

    Neuronpedia

    INDEX
    Explanations

    phrases like looking for

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AtIndexPath
    0.46
    უნ
    0.44
    िमम
    0.41
    мей
    0.40
    配套
    0.40
     अनिवार्य
    0.39
    निर्भर
    0.39
     observability
    0.38
    েকের
    0.38
     oxyd
    0.38
    POSITIVE LOGITS
     hired
    0.49
     options
    0.49
    options
    0.48
    Hire
    0.46
     Hire
    0.45
     Options
    0.45
     :,
    0.45
     Best
    0.43
    Best
    0.42
     gifts
    0.42
    Act Density 0.002%

    No Known Activations