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

    Neuronpedia

    INDEX
    Explanations

    mathematical reasoning

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ო�
    -0.09
     ïa
    -0.08
    ngort
    -0.08
     Newark
    -0.08
     Parc
    -0.08
     ചെന്ന
    -0.08
    ოფ
    -0.08
    ოუ�
    -0.08
     ลงทะเบียนฟรี
    -0.08
     Tah
    -0.08
    POSITIVE LOGITS
    ِ
    0.07
    ांस
    0.07
     ele
    0.07
    )**
    0.07
    967
    0.07
    ांव
    0.07
     decorator
    0.07
    ाशी
    0.07
    .cap
    0.07
    953
    0.06
    Act Density 0.196%

    No Known Activations