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

    Neuronpedia

    INDEX
    Explanations

    HashMap

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    NSMutableArray
    0.51
    マップ
    0.46
     homologs
    0.46
    ListAdapter
    0.44
     NSMutableArray
    0.41
     histogram
    0.41
    emap
    0.41
     कार्तिक
    0.40
     histograms
    0.40
     socketList
    0.40
    POSITIVE LOGITS
    Ха
    0.56
     HM
    0.51
     Ха
    0.51
    HM
    0.47
     HA
    0.45
    哈
    0.44
     Hem
    0.42
     Hack
    0.42
    aha
    0.41
     Hash
    0.41
    Act Density 0.002%

    No Known Activations