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

    Neuronpedia

    INDEX
    Explanations

    how somebody creates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    그러나
    0.40
     그러나
    0.38
     HashTable
    0.36
     Однако
    0.34
    <unused2002>
    0.33
     tcpHeader
    0.33
     tačiau
    0.33
     defaultdict
    0.32
    <unused2130>
    0.32
     pInBuffer
    0.32
    POSITIVE LOGITS
     somebody
    0.46
     harming
    0.43
     people
    0.42
     someone
    0.42
     loosing
    0.41
     foreigners
    0.40
     persons
    0.40
     fantasies
    0.40
     enem
    0.40
     Covid
    0.39
    Act Density 0.409%

    No Known Activations