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

    Neuronpedia

    INDEX
    Explanations

    equal to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    asser
    0.52
    ዖ
    0.52
    정
    0.51
    단
    0.50
    тым
    0.50
    자로
    0.49
    క
    0.48
    роди
    0.47
    렌
    0.47
    ージャ
    0.47
    POSITIVE LOGITS
     Mutant
    0.50
     AT
    0.45
     FU
    0.44
     Therapist
    0.44
     FUT
    0.44
    FACT
    0.43
     ATR
    0.43
     bookcase
    0.43
     RAIL
    0.43
     CNT
    0.43
    Act Density 0.001%

    No Known Activations