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

    Neuronpedia

    INDEX
    Explanations

    processors ache

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Typ
    0.40
     Али
    0.36
    Racing
    0.36
     वर्षों
    0.36
    voices
    0.36
    ⵍ
    0.35
     Pét
    0.35
    弜
    0.35
     lLoginID
    0.34
    ulle
    0.34
    POSITIVE LOGITS
     data
    0.40
     grapefruit
    0.39
    iž
    0.39
     શા
    0.38
     Rue
    0.37
     medications
    0.37
     entry
    0.36
     데이터
    0.36
     Entry
    0.36
     שמ
    0.36
    Act Density 0.006%

    No Known Activations