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

    Neuronpedia

    INDEX
    Explanations

    statement

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Rock
    -0.07
     palm
    -0.07
    belt
    -0.06
    두
    -0.06
     "@"
    -0.06
     cool
    -0.06
     lorsque
    -0.06
    Wait
    -0.06
    	slot
    -0.06
     Mesh
    -0.06
    POSITIVE LOGITS
    atırım
    0.07
    632
    0.06
    nač
    0.06
    opcode
    0.06
     Ryan
    0.06
     neph
    0.06
     Ezek
    0.06
    142
    0.06
    ening
    0.06
     constitutional
    0.06
    Act Density 0.020%

    No Known Activations