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

    Neuronpedia

    INDEX
    Explanations

    academic papers and code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     fanns
    -0.82
     romero
    -0.81
     supo
    -0.79
    表单
    -0.78
     vann
    -0.77
     génie
    -0.77
     KeyError
    -0.76
    áva
    -0.76
     <?
    -0.75
     SQLException
    -0.75
    POSITIVE LOGITS
     barricade
    0.82
    曹
    0.81
     proyec
    0.81
     cafeteria
    0.79
     rodzaj
    0.79
     pronouncing
    0.78
     Founding
    0.77
    ৈ
    0.77
     віта
    0.75
     Gründen
    0.75
    Act Density 0.001%

    No Known Activations