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

    Neuronpedia

    INDEX
    Explanations

    grammar

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     있으며
    -0.07
    ("${
    -0.06
    websocket
    -0.06
    _sources
    -0.06
    nes
    -0.06
     autobiography
    -0.06
    irus
    -0.06
     вне
    -0.06
     migli
    -0.06
    .getId
    -0.06
    POSITIVE LOGITS
    ्दर
    0.08
     cih
    0.07
    ーカー
    0.06
     tisk
    0.06
     Společ
    0.06
     menj
    0.06
     WOM
    0.06
    ώ
    0.06
     cq
    0.06
    dın
    0.06
    Act Density 0.364%

    No Known Activations