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

    Neuronpedia

    INDEX
    Explanations

    animal names, dog breeds

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    వారు
    0.90
    xit
    0.89
    kb
    0.88
    にし
    0.85
     relações
    0.84
    ojen
    0.83
     ITIS
    0.83
     I
    0.83
    iyy
    0.82
    kte
    0.80
    POSITIVE LOGITS
    ید
    0.81
    stairs
    0.79
    Ջ
    0.75
    не
    0.75
    یرے
    0.74
    代引不可
    0.74
    Number
    0.73
    Cheers
    0.73
    Ꭲ
    0.73
    巽
    0.73
    Act Density 0.013%

    No Known Activations