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

    Neuronpedia

    INDEX
    Explanations

    specific noun followed by descriptor

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    琲
    0.43
     brilliant
    0.38
     Rapids
    0.37
    쨌
    0.37
     orbits
    0.36
     SC
    0.36
     Lu
    0.36
     brilliantly
    0.35
     generals
    0.35
     Generals
    0.35
    POSITIVE LOGITS
    ಲಿನ
    0.46
    Thin
    0.45
    -',
    0.43
    manın
    0.43
    Sheet
    0.42
    unload
    0.42
    ൊരു
    0.41
    "',
    0.41
     ψ
    0.41
     '|
    0.41
    Act Density 0.000%

    No Known Activations