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

    Neuronpedia

    INDEX
    Explanations

    Math equations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ziu
    -0.08
     ostvar
    -0.08
    ciu
    -0.08
    Thong
    -0.08
    zech
    -0.08
    Serializable
    -0.08
     બહ
    -0.07
    最多
    -0.07
    -Compatible
    -0.07
     Praia
    -0.07
    POSITIVE LOGITS
    াপন
    0.08
    ー�
    0.08
    ারণ
    0.08
     underscores
    0.08
    ғат
    0.08
    ল্ল
    0.07
    রের
    0.07
    াপ
    0.07
     сияқты
    0.07
    >If
    0.07
    Act Density 0.001%

    No Known Activations