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

    Neuronpedia

    INDEX
    Explanations

    Court

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Albert
    -0.06
    .dtd
    -0.06
    define
    -0.06
    Gravity
    -0.06
     Haley
    -0.06
    Aj
    -0.06
     Shrine
    -0.06
     submarines
    -0.06
     frail
    -0.06
    	Color
    -0.06
    POSITIVE LOGITS
     circumstance
    0.07
    -created
    0.07
    -Christian
    0.07
    DOWN
    0.06
    ฟ
    0.06
     dựng
    0.06
    ाइट
    0.06
     timeout
    0.06
    hang
    0.06
     file
    0.06
    Act Density 0.004%

    No Known Activations