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

    Neuronpedia

    INDEX
    Explanations

    used car prices

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     मिळते
    0.39
     Ceux
    0.39
    ạo
    0.38
    ampilan
    0.38
    ânia
    0.38
    ospin
    0.38
    senior
    0.37
    egang
    0.37
    gruntled
    0.37
    adau
    0.37
    POSITIVE LOGITS
     APR
    0.42
    APR
    0.42
     LINE
    0.40
    Line
    0.38
     unifying
    0.38
    コイル
    0.38
    \(
    0.37
    Packet
    0.37
    虾
    0.37
     cancer
    0.37
    Act Density 0.003%

    No Known Activations