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

    Neuronpedia

    INDEX
    Explanations

    sauce matters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    由于
    0.71
    configuring
    0.68
    哪些
    0.66
     aşağıdaki
    0.65
     بسبب
    0.65
    ressione
    0.65
    heureusement
    0.65
    Due
    0.64
     вследствие
    0.64
    Stim
    0.63
    POSITIVE LOGITS
     matters
    4.31
     matter
    4.00
     mattered
    3.78
     Matters
    3.77
     Matter
    3.54
    matter
    3.33
     MATTER
    3.19
    Matter
    3.16
     मैटर
    2.40
     counts
    2.18
    Act Density 0.340%

    No Known Activations