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

    Neuronpedia

    INDEX
    Explanations

    JSON string values

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    㳒
    0.37
    sieh
    0.34
     paramInt
    0.34
    ළ
    0.33
     Aussi
    0.32
    insular
    0.32
    сія
    0.32
    র্ব
    0.31
     weer
    0.31
    噦
    0.31
    POSITIVE LOGITS
     data
    0.55
     filename
    0.52
    csv
    0.51
     데이터
    0.51
     invoice
    0.50
     csv
    0.50
     CSV
    0.49
     json
    0.49
     pokemon
    0.49
    Spotify
    0.49
    Act Density 0.057%

    No Known Activations