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

    Neuronpedia

    INDEX
    Explanations

    encryption used, toaster function

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    轵
    0.45
     Importantly
    0.39
     Bacterial
    0.38
    physiological
    0.37
     aswell
    0.37
    ட்சத்திர
    0.36
    لیکن
    0.36
     Physiological
    0.35
    fastq
    0.35
     Differentiation
    0.35
    POSITIVE LOGITS
     بين
    0.42
    ном
    0.40
     between
    0.39
    AY
    0.39
     calific
    0.38
     fellow
    0.38
    டித்து
    0.38
    ickeys
    0.37
     licenc
    0.37
     cumul
    0.37
    Act Density 0.000%

    No Known Activations