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

    Neuronpedia

    INDEX
    Explanations

    "Here's why" explanation marker

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    TZ
    0.41
     Spect
    0.39
     Synt
    0.39
    Synthetic
    0.38
    Va
    0.38
     Chip
    0.37
    TS
    0.37
     Va
    0.37
     Synthetic
    0.36
     スタッドレス
    0.36
    POSITIVE LOGITS
     জলের
    0.47
    explain
    0.41
     explain
    0.40
    реи
    0.38
    Fact
    0.37
    သွ
    0.37
     кожи
    0.36
    гри
    0.36
     округа
    0.36
    жей
    0.35
    Act Density 0.032%

    No Known Activations